Versionen vergleichen von : A Survey on Sentiment and Emotion Analysis for Computational Literary Studies

AltNeu
1A Survey on Sentiment and Emotion Analysis for Computational Literary Studies 1A Survey on Sentiment and Emotion Analysis for Computational Literary Studies
2 <div id="caption"><span class="Z3988" title="url_ver=Z39.88-2004&amp;ctx_ver=Z39.88-2004&amp;rfr_id=info%3Asid%2Fzotero.org%3A2&amp;rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&amp;rft.genre=article&amp;rft.atitle=A%20Survey%20on%20Sentiment%20and%20Emotion%20Analysis%20for%20Computational%20Literary%20Studies&amp;rft.au=Evgeny%20Kim&amp;rft.au=Roman%20Klinger&amp;rft.series=Zeitschrift%20f%C3%BCr%20digitale%20Geisteswissenschaften&amp;rft.date=2016-07-08&amp;rft_id=http://dx.doi.org/10.17175/2019_008&amp;rft.language=de&amp;rft.rights=CC BY-SA 4.0"></span><div> 2 <body>
3 <div id="caption"><span class="Z3988" title="url_ver=Z39.88-2004&amp;ctx_ver=Z39.88-2004&amp;rfr_id=info%3Asid%2Fzotero.org%3A2&amp;rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&amp;rft.genre=article&amp;rft.atitle=A%20Survey%20on%20Sentiment%20and%20Emotion%20Analysis%20for&#xA;%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20Computational%20Literary%20Studies&amp;rft.au=Evgeny%20Kim&amp;rft.au=Roman%20Klinger&amp;rft.series=Zeitschrift%20f%C3%BCr%20digitale%20Geisteswissenschaften&amp;rft.date=2019-12-16&amp;rft_id=http://dx.doi.org/10.17175/2019_008_v2&amp;rft.language=en&amp;rft.rights=CC BY-SA 4.0"></span><div>
3 <div style="margin: 1em 0 1em 0;">Evgeny Kim <a href="javascript:switchlayer('author1');"><img style="margin-left: 1%" src="/sites/default/files/arrow-down.png" alt="Autoreninformationen"></a></div> 4 <div style="margin: 1em 0 1em 0;">Evgeny Kim <a href="javascript:switchlayer('author1');"><img style="margin-left: 1%" src="/sites/default/files/arrow-down.png" alt="Autoreninformationen"></a></div>
4 <div style="display:none; width:100%; background-color: #fafafa;" id="author1"> Kontakt: <a href="mailto:evgeny.kim@ims.uni-stuttgart.de">evgeny.kim@ims.uni-stuttgart.de</a><br>Institution: Universität Stuttgart, Institut für Maschinelle Sprachverarbeitung <br>GND: <a href=" http://d-nb.info/gnd/1193672481" target="_blank:">1193672481</a><br>ORCID: <a href="https://orcid.org/0000-0001-6822-6709" target="_blank:">0000-0001-6822-6709</a><br></div> 5 <div style="display:none; width:100%; background-color: #fafafa;" id="author1"> Kontakt: <a href="mailto:evgeny.kim@ims.uni-stuttgart.de">evgeny.kim@ims.uni-stuttgart.de</a><br>Institution: Universität Stuttgart, Institut für Maschinelle
6 Sprachverarbeitung <br>GND: <a href=" http://d-nb.info/gnd/1193672481" target="_blank:">1193672481</a><br>ORCID: <a href="https://orcid.org/0000-0001-6822-6709" target="_blank:">0000-0001-6822-6709</a><br></div>
5 <div style="margin: 1em 0 1em 0;">Roman Klinger <a href="javascript:switchlayer('author2');"><img style="margin-left: 1%" src="/sites/default/files/arrow-down.png" alt="Autoreninformationen"></a></div> 7 <div style="margin: 1em 0 1em 0;">Roman Klinger <a href="javascript:switchlayer('author2');"><img style="margin-left: 1%" src="/sites/default/files/arrow-down.png" alt="Autoreninformationen"></a></div>
6 <div style="display:none; width:100%; background-color: #fafafa;" id="author2"> Kontakt: <a href="mailto:roman.klinger@ims.uni-stuttgart.de">roman.klinger@ims.uni-stuttgart.de</a><br>Institution: Universität Stuttgart, Institut für Maschinelle Sprachverarbeitung <br>GND: <a href=" http://d-nb.info/gnd/173873820" target="_blank:">173873820</a><br>ORCID: <a href="https://orcid.org/0000-0002-2014-6619" target="_blank:">0000-0002-2014-6619</a><br></div> 8 <div style="display:none; width:100%; background-color: #fafafa;" id="author2"> Kontakt: <a href="mailto:roman.klinger@ims.uni-stuttgart.de">roman.klinger@ims.uni-stuttgart.de</a><br>Institution: Universität Stuttgart, Institut für Maschinelle
9 Sprachverarbeitung <br>GND: <a href=" http://d-nb.info/gnd/173873820" target="_blank:">173873820</a><br>ORCID: <a href="https://orcid.org/0000-0002-2014-6619" target="_blank:">0000-0002-2014-6619</a><br></div>
7 </div> 10 </div>
9 <hr class="one"> 12 <hr class="one">
10 <p><span class="bolder">DOI: </span><a href="http://dx.doi.org/10.17175/2019_008">10.17175/2019_008</a></p> 13 <p><span class="bolder">DOI: </span><a href="http://dx.doi.org/10.17175/2019_008_v2">10.17175/2019_008_v2</a></p>
11 <p><span class="bolder">Nachweis im OPAC der Herzog August Bibliothek: </span><a href="http://opac.lbs-braunschweig.gbv.de/DB=2/XMLPRS=N/PPN?PPN=167855300X " target="_blank">167855300X </a></p> 14 <p><span class="bolder">Nachweis im OPAC der Herzog August Bibliothek: </span><a href="http://opac.lbs-braunschweig.gbv.de/DB=2/XMLPRS=N/PPN?PPN=176443949X " target="_blank">176443949X</a></p>
12 <p><span class="bolder">Erstveröffentlichung: </span>16.12.2019 15 <p><span class="bolder">Erstveröffentlichung: </span>16.12.2019
13 </p> 16 </p>
17<p><span class="bolder">Version 2.0: </span>23.07.2021
18 </p
14 <p><span class="bolder">Lizenz:</span> Sofern nicht anders angegeben <a href="https://creativecommons.org/licenses/by-sa/4.0/" rel="license" target="_blank"><img alt="Creative Commons Lizenzvertrag" src="/themes/zfdg/images/licensebuttons/l/by-sa/4.0/80x15.png"><br></a></p> 19 <p><span class="bolder">Lizenz:</span> Sofern nicht anders angegeben <a href="https://creativecommons.org/licenses/by-sa/4.0/" rel="license" target="_blank"><img alt="Creative Commons Lizenzvertrag" src="/themes/zfdg/images/licensebuttons/l/by-sa/4.0/80x15.png"><br></a></p>
16 <div id="info2"> 21 <div id="info2">
17 <p><span class="bolder">Medienlizenzen: </span>Medienrechte liegen bei den Autoren 22 <p><span class="bolder">Medienlizenzen: </span>Medienrechte liegen bei den Autor*innen
18 </p> 23 </p>
19 <p><span class="bolder">Letzte Überprüfung aller Verweise: </span>27.11.2019 24 <p><span class="bolder">Letzte Überprüfung aller Verweise: </span>22.07.2021
20 </p> 25 </p>
22 </p> 27 </p>
23 <p><span class="bolder">Empfohlene Zitierweise: </span>Evgeny Kim, Roman Klinger: A Survey on Sentiment and Emotion Analysis for Computational Literary Studies. In: Zeitschrift für digitale Geisteswissenschaften. Wolfenbüttel 2019. text/html Format. DOI: <a href="http://dx.doi.org/10.17175/2019_008">10.17175/2019_008</a></p> 28 <p><span class="bolder">Empfohlene Zitierweise: </span>Evgeny Kim, Roman Klinger: A Survey on Sentiment and Emotion Analysis for
29 Computational Literary Studies. In: Zeitschrift für digitale Geisteswissenschaften. Erstveröffentlichung vom 16.12.2019. Version 2.0 vom 23.07.2021. Wolfenbüttel 2021. text/html Format. DOI: <a href="http://dx.doi.org/10.17175/2019_008_v2">10.17175/2019_008_v2</a></p>
24 <hr class="one"> 30 <hr class="one">
26 </div> 32 </div>
27 <div class="content"> 33 <div class="content"><a name="div2"> </a><div id="abstract">
28 <div id="abstract_en" class="abstract"> 34 <div id="abstract_de" class="abstract">
29 <h1>Abstract</h1> 35 <h1>Abstract</h1>Emotionen sind ein wesentlicher Bestandteil fesselnder Erzählungen:
30 <p>Emotions are a crucial part of compelling narratives: literature tells us about 36 Literatur erzählt uns von Menschen mit Zielen, Wünschen, Leidenschaften
31 people with goals, desires, passions, and intentions. In the past, the 37 und Absichten. Die Analyse von Emotionen ist Teil des breiteren und
32 affective dimension of literature was mainly studied in the context of literary 38 größeren Feldes der Sentimentanalyse und findet in der
33 hermeneutics. However, with the emergence of the research field known as 39 Literaturwissenschaft zunehmend Beachtung. In der Vergangenheit wurde
34 <span style="color:#035151"><i>Digital Humanities</i></span> (DH), some studies of emotions in a literary context have 40 die affektive Dimension der Literatur hauptsächlich im Rahmen der
35 taken a computational turn. Given the fact that DH is still being formed as a 41 literarischen Hermeneutik untersucht. Mit dem Aufkommen der Digital
36 field, this direction of research can be rendered relatively new. In this 42 Humanities (DH) als Forschungsfeld, haben jedoch einige Studien über
37 survey, we offer an overview of the existing body of research on sentiment and 43 Emotionen im literarischen Kontext eine computergestützte Wendung
38 emotion analysis as applied to literature. The research under review deals with 44 genommen. In Anbetracht der Tatsache, dass sich die DH als Feld noch im
39 a variety of topics including tracking dramatic changes of a plot development, 45 Aufbau befindet, kann diese Forschungsrichtung als relativ neu
40 network analysis of a literary text, and understanding the emotionality of 46 bezeichnet werden. In dieser Übersicht bieten wir einen Überblick über
41 texts, among other topics. 47 die bestehende Forschung zur Emotionsanalyse in der Literatur. Die
42 </p> 48 untersuchte Forschungsliteratur befasst sich mit einer Vielzahl von
49 Themen, darunter die Veränderungen der emotionalen Konnotation im
50 Verlauf eines Texts, die Netzwerkanalyse eines literarischen Textes und
51 das Verstehen der Emotionalität von Texten, neben anderen Themen.
52 Basierend auf diesem Überblick weisen wir auf eine Reihe von
53 verbleibenden Herausforderungen hin, die vielversprechende zukünftige
54 Forschungsrichtungen darstellen.
43 </div> 55 </div>
44 <hr class="one"> 56 <hr class="one">
45 <div id="abstract_de" class="abstract"> 57 <div id="abstract_en" class="abstract">Emotions are a crucial part of compelling narratives: literature tells us
46<p>Emotionen sind ein wichtiger Bestandteil überzeugender Erzählungen, 58 about people with goals, desires, passions, and intentions. Emotion
47 Literatur beschreibt schließlich Menschen und ihre Ziele, Wünsche, 59 analysis is part of the broader and larger field of sentiment analysis,
48 Leidenschaften und Absichten. In der Vergangenheit wurde diese affektive 60 and receives increasing attention in literary studies. In the past, the
49 Dimension hauptsächlich im Rahmen der literarischen Hermeneutik 61 affective dimension of literature was mainly studied in the context of
50 untersucht. Mit dem Aufkommen des Forschungsfeldes <span style="color:#035151"><i>Digital Humanities</i></span> 62 literary hermeneutics. However, with the emergence of the research field
51 (DH) wurde jedoch in einigen Studien bezüglich des Aspekts der Emotionen 63 known as Digital Humanities (DH), some studies of emotions in a literary
52 im literarischen Kontext eine Wende hin zu komputationellen Methoden 64 context have taken a computational turn. Given the fact that DH is still
53 vorgenommen. Diese Forschungsrichtung ist aktuell durch die Prozesse in 65 being formed as a field, this direction of research can be rendered
54 den DH in einer Neugestaltung. In diesem Artikel berichten wir über den aktuellen 66 relatively new. In this survey, we offer an overview of the existing
55 Forschungsstand zur 67 body of research on emotion analysis as applied to literature. The
56 Sentiment- und Emotionsanalyse zur Analyse von Literatur. Wir behandeln 68 research under review deals with a variety of topics including tracking
57 eine Vielzahl von Themen, wie zum Beispiel die Veränderungen der 69 dramatic changes of a plot development, network analysis of a literary
58 emotionalen Konnotation im Verlauf eines Texts, der Netzwerkanalyse 70 text, and understanding the emotionality of texts, among other topics.
59 eines literarischen Textes und dem Verständnis der Emotionalität von Texten. 71 Based on this review, we point to a set of remaining challenges that
60 </p> 72 constitute promising future research directions.
61 </div> 73 </div>
62<hr class="one"> 74 <hr class="one">
63<div>Zu diesem Artikel ist eine überarbeitete Version erschienen: <a href="https://zfdg.de/2019_008">Version 2</a></div> 75 <div id="versionsbox">
64 <hr class="one"> 76 <h3>Version 2.0 (05.07.2021)</h3>
77 <p>Es wurden folgende Änderungen vorgenommen: Inhaltliche Anpassungen, wie sie von
78 den Gutachten angemerkt worden sind. Austausch der Tab. 1. Aktualisierung und Ergänzung
79 der
80 bibliographischen Angaben. Formale Korrekturen.
81 </p>
82 </div>
65 <div id="headings"><br><br><hr class="two"><br><ul> 83 <div id="headings"><br><br><hr class="two"><br><ul>
66 <li><a href="#hd1">1 Introduction and Motivation</a></li> 84 <li><a href="#hd1">1 Introduction and Motivation</a></li>
67 <li><a href="#hd2">1.1 Emotions and Arts</a></li> 85 <li><a href="#hd2">1.1 Scope of this Survey</a></li>
68 <li><a href="#hd3">2 Affect and Emotion</a></li> 86 <li><a href="#hd3">1.2 Emotion Analysis and Digital Humanities</a></li>
69 <li><a href="#hd4">2.1 Ekman’s Theory of Basic Emotions</a></li> 87 <li><a href="#hd4">1.3 Emotions and Arts</a></li>
70 <li><a href="#hd5">2.2 Plutchik’s Wheel of Emotions</a></li> 88 <li><a href="#hd5">2 Affect and Emotion</a></li>
71 <li><a href="#hd6">2.3 Russel’s Circumplex Model</a></li> 89 <li><a href="#hd6">2.1 Ekman’s Theory of Basic Emotions</a></li>
72 <li><a href="#hd7">3 Emotion Analysis in Non-computational Literary Studies</a></li> 90 <li><a href="#hd7">2.2 Plutchik’s Wheel of Emotions</a></li>
73 <li><a href="#hd8">4 Emotion and Sentiment Analysis in Computational Literary Studies</a></li> 91 <li><a href="#hd8">2.3 Russel’s Circumplex Model </a></li>
74 <li><a href="#hd9">4.1 Emotion Classification</a></li> 92 <li><a href="#hd9">3 Emotion Analysis in Non-computational Literary Studies</a></li>
75 <li><a href="#hd10">4.1.1 Classification based on emotions</a></li> 93 <li><a href="#hd10">4 Emotion and Sentiment Analysis in Computational Literary Studies</a></li>
76 <li><a href="#hd11">4.1.2 Classification of happy ending vs. non-happy endings</a></li> 94 <li><a href="#hd11">4.1 Emotion Classification</a></li>
77 <li><a href="#hd12">4.2 Genre and Story-type Classification</a></li> 95 <li><a href="#hd12">4.1.1 Classification based on emotions</a></li>
78 <li><a href="#hd13">4.2.1 Story-type clustering</a></li> 96 <li><a href="#hd13">4.1.2 Classification of happy ending vs. non-happy
79 <li><a href="#hd14">4.2.2 Genre classification</a></li> 97 endings</a></li>
80 <li><a href="#hd15">4.3 Temporal Change of Sentiment</a></li> 98 <li><a href="#hd14">4.2 Genre and Story-type Classification</a></li>
81 <li><a href="#hd16">4.3.1 Topography of emotions</a></li> 99 <li><a href="#hd15">4.2.1 Story-type clustering</a></li>
82 <li><a href="#hd17">4.3.2 Tracking sentiment</a></li> 100 <li><a href="#hd16">4.2.2 Genre classification</a></li>
83 <li><a href="#hd18">4.3.3 Sentiment recognition in historical texts</a></li> 101 <li><a href="#hd17">4.3 Structural Changes of Sentiment</a></li>
84 <li><a href="#hd19">4.4 Character Network Analysis and Relationship Extraction</a></li> 102 <li><a href="#hd18">4.3.1 Topography of emotions</a></li>
85 <li><a href="#hd20">4.4.1 Sentiment dynamics between characters</a></li> 103 <li><a href="#hd19">4.3.2 Tracking sentiment</a></li>
86 <li><a href="#hd21">4.4.2 Character analysis and character relationships</a></li> 104 <li><a href="#hd20">4.3.3 Sentiment recognition in historical
87 <li><a href="#hd22">4.5 Other Types of Emotion Analysis</a></li> 105 texts</a></li>
88 <li><a href="#hd23">4.5.1 Emotion flow analysis and visualization</a></li> 106 <li><a href="#hd21">4.4 Character Network Analysis and
89 <li><a href="#hd24">4.5.2 Miscellaneous</a></li> 107 Relationship Extraction</a></li>
90 <li><a href="#hd25">5 Discussion and Conclusion</a></li> 108 <li><a href="#hd22">4.4.1 Sentiment dynamics between
91 <li><a href="#hd26">Acknowledgements</a></li> 109 characters</a></li>
92 <li><a href="#hd27">Bibliographic References</a></li> 110 <li><a href="#hd23">4.4.2 Character analysis and character
93 <li><a href="#hd28">List of Figures with Captions</a></li> 111 relationships</a></li>
112 <li><a href="#hd24">4.5 Other Types of Emotion Analysis</a></li>
113 <li><a href="#hd25">4.5.1 Emotion flow analysis and
114 visualization</a></li>
115 <li><a href="#hd26">4.5.2 Miscellaneous</a></li>
116 <li><a href="#hd27">5 Discussion and Conclusion</a></li>
117 <li><a href="#hd28">Acknowledgements</a></li>
118 <li><a href="#hd29">Bibliographic References</a></li>
119 <li><a href="#hd30">List of Figures with Captions</a></li>
94 </ul> 120 </ul>
95 </div><br><div id="chapter"><a name="hd1"> </a><h2> 121 </div><br></div><a name="div3"> </a><div id="chapter"><a name="hd1"> </a><h2>
96 <div style="position:relative;width:90%;">1 Introduction and Motivation</div> 122 <div style="position:relative;width:90%;">1 Introduction and Motivation</div>
97 </h2> 123 </h2>
98 <p>This article deals with <i>emotion</i> and <i>sentiment</i> analysis in <span style="color:#035151"><i>computational literary studies</i></span>. 124 <p id="pid1"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid1">1</a>]</span>This article deals with <i>emotion</i> and <i>sentiment</i> analysis in <span style="color:#035151"><i>computational literary
99 Following Liu<a id="fna1" class="fn" href="#fn1" title="Liu 2015, p.2.">[1]</a>, we define sentiment as a 125 studies</i></span>. Following Liu,<a id="fna1" class="fn" href="#fn1" title="Liu 2015, p. 2.">[1]</a> we define sentiment as a <i>positive</i> or
100 <i>positive</i> or <i>negative</i> feeling 126 <i>negative</i> feeling underlying the opinion.
101 underlying the opinion. The term <i>opinion</i> in this sense is 127 Sometimes, sentiment analysis is interpreted synonymously to opinion mining,
102 close to <i>attitude</i> in psychology and both sentiment analysis 128 however strictly speaking, opinion mining is an application that makes use
103 and opinion mining are often used interchangeably. Sentiment analysis is an area of 129 of sentiment analysis and contextualizes polarity ratings in topics, aspects
104 computational linguistics that analyzes people’s sentiments and opinions regarding 130 and targets. Though sentiment analysis is primarily text-oriented, there are
105 different objects or topics. Though sentiment analysis is primarily text-oriented, 131 multimodal approaches as well.<a id="fna2" class="fn" href="#fn2" title="Soleymani et&nbsp;al. 2017.">[2]</a></p>
106 there are multimodal approaches as well.<a id="fna2" class="fn" href="#fn2" title="Soleymani et&nbsp;al. 2017.">[2]</a></p> 132 <p id="pid2"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid2">2</a>]</span>Another interpretation of the term <i>sentiment analysis</i>
107 <p>Defining the concept of <i>emotion</i> is a challenging task. As 133 is as broader description of a research field, which considers affective
108 Scherer puts it, defining emotion is a notorious problem.<a id="fna3" class="fn" href="#fn3" title="Scherer 2005, p. 695.">[3]</a> Indeed, different methodological and conceptual 134 computing applied to textual analysis. In this sense, it also includes the
109 approaches to dealing with emotions lead to different definitions. However, the 135 distinction into subjective or objective statements,<a id="fna3" class="fn" href="#fn3" title="Wiebe et al. 2004.">[3]</a> and, more recently, the field of emotion
110 majority of emotion theorists agree that emotions involve a set of expressive, 136 analysis.Defining the concept of <i>emotion</i> is a
111 behavioral, physiological, and phenomenological features.<a id="fna4" class="fn" href="#fn4" title="Scarantino 2016, p. 36.">[4]</a> In this view, an emotion can be defined as an 137 challenging task. As Scherer puts it, »defining emotion is a notorious
112 integrated feeling state involving physiological changes, motor-preparedness, 138 problem«.<a id="fna4" class="fn" href="#fn4" title="Scherer 2005, p. 1.">[4]</a>
113 cognitions about action, and inner experiences that emerges from an appraisal of the 139 Indeed, different methodological and conceptual approaches to dealing with
114 self or situation.<a id="fna5" class="fn" href="#fn5" title="Mayer et&nbsp;al. 2008, p. 510.">[5]</a></p> 140 emotions lead to different definitions. However, the majority of emotion
115 <p>Similar to sentiment, emotions can be analyzed computationally. However, the goal 141 theorists agree that emotions involve a set of expressive, behavioral,
116 of 142 physiological, and phenomenological features.<a id="fna5" class="fn" href="#fn5" title="Scarantino 2016, p. 36.">[5]</a> In this view, an emotion can be defined
117 emotion analysis is to recognize the emotion, rather than sentiment, which makes it 143 as »an integrated feeling state involving physiological changes,
118 a 144 motor-preparedness, cognitions about action, and inner experiences that
119 more difficult task as differences between emotions are subtler than those between 145 emerges from an appraisal of the self or situation«.<a id="fna6" class="fn" href="#fn6" title="Mayer et&nbsp;al. 2008, p. 2.">[6]</a></p>
120 positive and negative. 146 <p id="pid3"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid3">3</a>]</span>Similar to sentiment, emotions can be analyzed computationally. However, the
121 </p> 147 goal of emotion analysis is to recognize the emotion, rather than sentiment,
122 <p>Although sentiment and emotion analysis are different tasks, our review of the 148 which makes it a more difficult task as differences between some emotion
123 literature shows that the use of either term is not always consistent. There are 149 classes are more subtle than those between positive and negative.
124 cases where researchers analyze only positive and negative aspects of a text but 150 </p>
125 refer to their analysis as emotion analysis. Likewise, there are cases where 151 <p id="pid4"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid4">4</a>]</span>Although sentiment and emotion analysis are different tasks, our review of
126 researchers look into a set of subjective feelings including emotions but call it 152 the literature shows that the use of either term is not always consistent.
127 sentiment analysis. Hence, to avoid confusion, in this survey, we use the terms <span style="color:#035151"><i>emotion analysis</i></span> and <span style="color:#035151"><i>sentiment analysis</i></span> 153 There are cases where researchers analyze only positive and negative aspects
128 interchangeably. In most cases, we follow the terminology used by the authors of the 154 of a text but refer to their analysis as emotion analysis. Likewise, there
129 papers we discuss (i.e., if they call emotions sentiments, we do the same). 155 are cases where researchers look into a set of subjective feelings including
130 </p> 156 emotions but call it sentiment analysis. Hence, to avoid confusion, in this
131 <p>Finally, we talk about sentiment and emotion analysis in the context of computational 157 survey, we use the terms <span style="color:#035151"><i>emotion analysis</i></span> and <span style="color:#035151"><i>sentiment analysis</i></span> interchangeably. In most cases, we
132 literary studies. Da defines computational literary studies as the statistical 158 follow the terminology used by the authors of the papers we discuss (i.e.,
133 representation of patterns discovered in text mining fitted to currently existing 159 if they call emotions sentiments, we do the same). However, our focus of
134 knowledge about literature, literary history, and textual production.<a id="fna6" class="fn" href="#fn6" title="Da 2019, p. 602.">[6]</a> Computational literary studies are 160 this survey is on emotion analysis, and we do not include the majority of
135 synonymous to <span style="color:#035151"><i>distant reading</i></span><a id="fna7" class="fn" href="#fn7" title="Moretti 2005.">[7]</a> and <span style="color:#035151"><i>digital 161 work that focuses on binary polarities.
136 literary studies</i></span>,<a id="fna8" class="fn" href="#fn8" title="Hoover et&nbsp;al. 2014.">[8]</a> 162 </p>
137 each of which refers to the practice of running a textual analysis on a computer to 163 <p id="pid5"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid5">5</a>]</span>Finally, we talk about sentiment and emotion analysis in the context of
138 yield quantitative results. In this survey, we use all of these terms interchangeably 164 computational literary studies. Da defines computational literary studies as
139 and when we refer to digital humanities as a field, we refer to those groups of 165 the statistical representation of patterns discovered in text mining fitted
140 researchers whose primary objects of study are texts. 166 to currently existing knowledge about literature, literary history, and
141 </p> 167 textual production.<a id="fna7" class="fn" href="#fn7" title="Da 2019, p. 602.">[7]</a>
142 <div id="subchapter"><a name="hd2"> </a><h3> 168 Computational literary studies are closely related to the concepts of <span style="color:#035151"><i>distant reading</i></span><a id="fna8" class="fn" href="#fn8" title="Moretti 2005.">[8]</a> and <span style="color:#035151"><i>digital
143 <div style="position:relative;width:90%;">1.1 Emotions and Arts</div> 169 literary studies</i></span>,<a id="fna9" class="fn" href="#fn9" title="Hoover et&nbsp;al. 2014.">[9]</a> each of which refers to the practice of running a textual
170 analysis on a computer to yield quantitative results. In this survey, we use
171 all of these terms interchangeably and when we refer to digital humanities
172 as a field, we refer to those groups of researchers whose primary objects of
173 study are texts.
174 </p><a name="div4"> </a><div id="subchapter"><a name="hd2"> </a><h3>
175 <div style="position:relative;width:90%;">1.1 Scope of this Survey</div>
144 </h3> 176 </h3>
145 <p>Much of our daily experiences influence and are influenced by the emotions we 177 <p id="pid6"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid6">6</a>]</span>This survey provides an overview of work which aims at understanding or
146 experience.<a id="fna9" class="fn" href="#fn9" title="Schwarz 2000, p. 433.">[9]</a> This experience is 178 analyzing emotions in literature. We include studies that answer a
147 not limited to real events. People can feel emotions because they are reading a novel 179 concrete research question from the field of literary studies with
148 or watching a play or a movie.<a id="fna10" class="fn" href="#fn10" title="Johnson-Laird / Oatley 2016, passim; Djikic et&nbsp;al. 2009, passim.">[10]</a> There is a growing 180 computational methods. We do only consider publications in English that
149 body of literature that pinpoints the importance of emotions for literary comprehension, 181 have been quality-assessed by peer review (except for few exceptions).
150 <a id="fna11" class="fn" href="#fn11" title="Robinson 2005; Hogan 2010; Hogan 2011; Bal / Veltkamp 2013; Djikic et&nbsp;al. 2013; Johnson 2012; Samur et&nbsp;al. 2018.">[11]</a> as well as research 182 We exclude efforts of corpus creation and annotation, if those corpora
151 that recognizes the deliberate choices people make with regard to their emotional 183 have not been used for a further research study to limit the scope of
152 states when seeking narrative enjoyment such as a book or a film<a id="fna12" class="fn" href="#fn12" title="Zillmann et&nbsp;al. 1980; Ross 1999; Bryant / Zillmann 1984; Oliver 2008; Mar et&nbsp;al. 2011.">[12]</a> 184 this survey (though such work is clearly relevant and important) and
153 The link between emotions and arts in general is a matter of debate that dates back 185 software development efforts if the associated papers do not aim at
154 to the Ancient period, particularly to Plato, who viewed passions and desires as the 186 contributing to answering a research question. Similarly, we do mostly
155 lowest kind of knowledge and treated poets as undesirable members in his ideal 187 exclude reports on ongoing research efforts, if they do not contribute a
156 society.<a id="fna13" class="fn" href="#fn13" title="Plato 1969 , passim.">[13]</a> In contrast, Aristotle’s 188 novel understanding of a research question. Our literature research
157 view on emotive components of poetry expressed in his <i>Poetics</i><a id="fna14" class="fn" href="#fn14" title="Aristotle 1996, passim.">[14]</a> differed from Plato’s in that 189 started in the field of computational linguistics with the <a href="https://www.aclweb.org/anthology/" target="_blank">ACL Anthology</a> and
158 emotions do have great importance, particularly in the moral life of a person.<a id="fna15" class="fn" href="#fn15" title="De&nbsp;Sousa / Scarantino 2018.">[15]</a> In the late nineteenth 190 has been complemented by other research that cites such papers or is
159 century the emotion theory of arts stepped into the spotlight of philosophers. One 191 cited by them. We exclude papers from local digital humanities
160 of 192 conferences.
161 the first accounts on the topic is given by Leo Tolstoy in 1898 in his essay <i>What is Art?</i>.<a id="fna16" class="fn" href="#fn16" title="Tolstoy 1962, passim.">[16]</a> Tolstoy argues that art 193 </p>
162 can express emotions experienced in fictitious context and the degree to which the 194 <p id="pid7"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid7">7</a>]</span>The goal of this survey is to provide an overview of recent methods of
163 audience is convinced of them defines the success of the artistic work.<a id="fna17" class="fn" href="#fn17" title="Anderson / McMaster 1986, p. 3; Hogan 2010, p. 187; Piper / Jean&nbsp;So 2015.">[17]</a></p> 195 emotion and sentiment analysis as applied to a text. The survey is
164 <p>New methods of quantitative research emerged in humanities scholarship bringing forth 196 directed at researchers looking for an introduction to the existing
165 the so-called <i>digital revolution</i><a id="fna18" class="fn" href="#fn18" title="Lanham 1989.">[18]</a> and the transformation of the 197 research in the field of sentiment and emotion analysis of a (primarily,
166 field into what we know as digital humanities.<a id="fna19" class="fn" href="#fn19" title="Berry 2012; Schreibman et&nbsp;al. 2015.">[19]</a> The adoption of computational 198 literary) text. We do not not cover applications of emotion analysis in
167 methods of text analysis and data mining from the fields of then fast-growing areas 199 the areas of digital humanities that are not focused on text. Neither do
168 of computational linguistics and artificial intelligence provided humanities scholars 200 we provide an in-depth overview of all possible applications of emotion
169 with new tools of text analytics and data-driven approaches to theory 201 analysis in the computational context outside of the DH line of
170 formulation.<a id="fna20" class="fn" href="#fn20" title="Vanhoutte 2013, p. 142; Jockers / Underwood 2016, pp. 292f.">[20]</a></p> 202 research.
171 <p>To the best of our knowledge, the first work<a id="fna21" class="fn" href="#fn21" title="Anderson / McMaster 1982.">[21]</a> on a computer-assisted modeling of emotions in 203 </p>
172 literature appeared in 1982. Challenged by the question of why some texts are more 204 </div><a name="div5"> </a><div id="subchapter"><a name="hd3"> </a><h3>
173 interesting than others, Anderson and McMaster concluded that the emotional tone of 205 <div style="position:relative;width:90%;">1.2 Emotion Analysis and Digital Humanities</div>
174 a 206 </h3>
175 story can be responsible for the reader’s interest. The results of their study 207 <p id="pid8"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid8">8</a>]</span>Methods that apply emotion analysis can in general be categorized
176 suggest that a large-scale analysis of the emotional tone of a collection of texts 208 into (<a title="" href="#hd1">section 1</a>) dictionary-based methods, (<a title="" href="#hd5">chapter 2</a>) feature-based
177 is 209 machine-learning-based, and (<a title="" href="#hd9">section 3</a>) representation-learning/deep
178 possible with the help of a computer program. There are two implications of this 210 learning-based. Methods that apply statistical learning (<a title="" href="#hd8">section 2.3</a>) to
179 finding. First, they suggested that by identifying emotional tones of text passages 211 induce a model that takes text as input and output predictions rely
180 one can model affective patterns of a given text or a collection of texts, which in 212 in the majority of cases (in this field) on supervised approaches –
181 turn can be used to challenge or test existing literary theories. Second, their 213 a learning algorithm is presented with annotated data and needs to
182 approach to affect modeling demonstrates that the stylistic properties of texts can 214 output a model that can, as good as possible on unseen data, do such
183 be defined on the basis of their emotional interest and not only their linguistic 215 predictions. These approaches have advantages: The learner can
184 characteristics. With regard to these implications, this work is an important early 216 exploit (long-distant) dependencies between textual units, learn
185 piece as it laid out a roadmap for some of the basic applications of sentiment and 217 associations between semanic meaning and concepts to learn, and make
186 emotion analysis of texts, namely sentiment and emotion pattern recognition from text 218 use of semantic similarities between words; even those that have not
187 and computational text characterization based on sentiment and emotion. 219 been seen in training data. This comes at a cost – the need for
188 </p> 220 annotated data. The situation between the fields of computational
189 <p>With the development of research methods used by digital humanities researchers, the 221 linguistics and digital humanities differs substantially in this
190 number of approaches and goals of emotion and sentiment analysis in literature has 222 regard.
191 grown. The goal of this survey is to provide an overview of these recent methods of 223 </p>
192 emotion and sentiment analysis as applied to a text. The survey is directed at 224 <p id="pid9"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid9">9</a>]</span>The focus in computational linguistics is to develop methods to solve
193 researchers looking for an introduction to the existing research in the field of 225 a particular task – analyze syntax, respresent semantics, or develop
194 sentiment and emotion analysis of a (primarily, literary) text. The survey does not 226 well-performing classification methods, for instance for emotion
195 cover applications of emotion and sentiment analysis in the areas of digital 227 classification. Therefore, there exists a substantial body of
196 humanities that are not focused on text. Neither does it provide an in-depth overview 228 research on natural language processing which is essentially
197 of all possible applications of emotion analysis in the computational context outside 229 agnostic to the corpus. In fact, a method is typically evaluated on
198 of the DH line of research. 230 a set of different resources to prove its generalizability, and even
199 </p> 231 if a novel corpus is presented for future studies, this is compared
200 </div> 232 to existing resources. This comes with an advantage: Resources are
201 </div> 233 often built by domain experts, which are then used for further
202 <div id="chapter"><a name="hd3"> </a><h2> 234 analysis; the diversity might be limited, but is often sufficient
235 for model development.
236 </p>
237 <p id="pid10"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid10">10</a>]</span>In digital humanities, this situation differs substantially. The goal
238 is often not the development of a computational model that is able
239 to make predictions for the entirety of a field (which is of course
240 also not achieved in computational linguistics, but that is
241 sometimes claimed to be a goal). Instead, the object of research (a
242 particular text, a genre, an author, ...) is of higher importance.
243 This comes with a challenge: Annotators often need to be experts in
244 the particular domain, for a particular object of research.
245 </p>
246 <p id="pid11"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid11">11</a>]</span>That might be the reason, as we will see, that, in contrast to
247 research in computational linguistics, using lexicons of words
248 associated with the concepts of interest, receives some attention as
249 a methodological approach to emotion analysis. This comes at the
250 cost of accuracy, as such methods are (mostly) not able to interpret
251 the context appropriately (with some exceptions which embed
252 dictionaries with rules<a id="fna10" class="fn" href="#fn10" title="E.g. Shaikh 2009.">[10]</a>), however, it contributes the advantage of being transparent
253 not only with the predictions and the results, but also with the
254 analysis algorithm.
255 </p>
256 </div><a name="div6"> </a><div id="subchapter"><a name="hd4"> </a><h3>
257 <div style="position:relative;width:90%;">1.3 Emotions and Arts</div>
258 </h3>
259 <p id="pid12"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid12">12</a>]</span>Much of our daily experiences influence and are influenced by the emotions we
260 experience.<a id="fna11" class="fn" href="#fn11" title="Schwarz 2000, p. 433.">[11]</a> This experience is not limited to real events. People can
261 feel emotions because they are reading a novel or watching a play or a
262 movie.<a id="fna12" class="fn" href="#fn12" title="Johnson-Laird / Oatley 2016; Djikic et&nbsp;al. 2009.">[12]</a>
263 There is a growing
264 body of literature that pinpoints the importance of emotions for
265 literary comprehension,<a id="fna13" class="fn" href="#fn13" title="Robinson 2005; Hogan 2010; Hogan 2011; Bal / Veltkamp 2013; Djikic et&nbsp;al. 2013; Johnson 2012; Samur et&nbsp;al. 2018.">[13]</a>
266 as well as
267 research that recognizes the deliberate choices people make with
268 regard to their emotional states when seeking narrative
269 enjoyment such as a book or a film.<a id="fna14" class="fn" href="#fn14" title="Zillmann et&nbsp;al. 1980; Ross 1999; Bryant / Zillmann 1984; Oliver 2008; Mar et&nbsp;al. 2011.">[14]</a></p>
270 <p id="pid13"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid13">13</a>]</span>The link between emotions and arts in general is a matter of
271 debate that dates back to the Ancient period, particularly to
272 Plato, who viewed passions and desires as the lowest kind of
273 knowledge and treated poets as undesirable members in his ideal
274 society.<a id="fna15" class="fn" href="#fn15" title="Plato 1969.">[15]</a> In
275 contrast, Aristotle’s view on emotive components of poetry
276 expressed in his <i>Poetics</i><a id="fna16" class="fn" href="#fn16" title="Aristotle 1996.">[16]</a> differed from
277 Plato’s in that emotions do have great importance, particularly
278 in the moral life of a person.<a id="fna17" class="fn" href="#fn17" title="de&nbsp;Sousa / Scarantino 2018.">[17]</a> In the late nineteenth century the
279 emotion theory of arts stepped into the spotlight of
280 philosophers. One of the first accounts on the topic is given by
281 Leo Tolstoy in 1898 in his essay <i>What is Art?</i>.<a id="fna18" class="fn" href="#fn18" title="Tolstoy 1962.">[18]</a> Tolstoy
282 argues that art can express emotions experienced in fictitious
283 context and the degree to which the audience is convinced of
284 them defines the success of the artistic work.<a id="fna19" class="fn" href="#fn19" title="Anderson / McMaster 1986, p. 3; Hogan 2010, p. 187; Piper / Jean&nbsp;So 2015.">[19]</a></p>
285 <p id="pid14"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid14">14</a>]</span>New methods of quantitative research emerged in humanities
286 scholarship bringing forth the so-called <i>digital revolution</i><a id="fna20" class="fn" href="#fn20" title="Lanham 1989.">[20]</a> and the
287 transformation of the field into what we know as digital
288 humanities.<a id="fna21" class="fn" href="#fn21" title="Berry 2012; Schreibman et&nbsp;al. 2015.">[21]</a> The adoption of computational methods of
289 text analysis and data mining from the fields of then
290 fast-growing areas of computational linguistics and artificial
291 intelligence provided humanities scholars with new tools of text
292 analytics and data-driven approaches to theory formulation.<a id="fna22" class="fn" href="#fn22" title="Vanhoutte 2013, p. 142; Jockers / Underwood 2016, pp. 292f.">[22]</a></p>
293 <p id="pid15"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid15">15</a>]</span>To the best of our knowledge, the first work<a id="fna23" class="fn" href="#fn23" title="Anderson / McMaster 1982.">[23]</a> on a computer-assisted
294 modeling of emotions in literature appeared in 1982. Challenged
295 by the question of why some texts are more interesting than
296 others, Anderson and McMaster concluded that the
297 »emotional tone« of a story can be responsible
298 for the reader’s interest. The results of their study suggest
299 that a large-scale analysis of the »emotional tone«
300 of a collection of texts is possible with the help of a computer
301 program. There are two implications of this finding. First, they
302 suggested that by identifying emotional tones of text passages
303 one can model affective patterns of a given text or a collection
304 of texts, which in turn can be used to challenge or test
305 existing literary theories. Second, their approach to affect
306 modeling demonstrates that the stylistic properties of texts can
307 be defined on the basis of their emotional interest and not only
308 their linguistic characteristics. With regard to these
309 implications, this work is an important early piece as it laid
310 out a roadmap for some of the basic applications of sentiment
311 and emotion analysis of texts, namely sentiment and emotion
312 pattern recognition from text and computational text
313 characterization based on sentiment and emotion.
314 </p>
315 <p id="pid16"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid16">16</a>]</span>With the development of research methods used by digital
316 humanities researchers, the number of approaches and goals of
317 emotion and sentiment analysis in literature has grown.
318 </p>
319 </div>
320 </div><a name="div7"> </a><div id="chapter"><a name="hd5"> </a><h2>
203 <div style="position:relative;width:90%;">2 Affect and Emotion</div> 321 <div style="position:relative;width:90%;">2 Affect and Emotion</div>
204 </h2> 322 </h2>
205 <p>The history of emotion research has a long and rich tradition that followed Darwin’s 323 <p id="pid17"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid17">17</a>]</span>The history of emotion research has a long and rich tradition that followed
206 1872 publication of <i>The Expression of the Emotions in Man and Animals</i><a id="fna22" class="fn" href="#fn22" title="Darwin 1872, passim.">[22]</a>. The subject of emotion theories is vast 324 Darwin’s 1872 publication of <i>The Expression of the Emotions in Man and
207 and diverse. We refer the reader to Maria Gendron’s paper<a id="fna23" class="fn" href="#fn23" title="Gendron / Feldman&nbsp;Barrett 2009.">[23]</a> for a brief history of ideas about emotion 325 Animals</i>.<a id="fna24" class="fn" href="#fn24" title="Darwin 1872.">[24]</a> The subject of emotion theories
208 in psychology. Here, we will focus on three views on emotion that are popular in 326 is vast and diverse. We refer the reader to Maria Gendron’s paper<a id="fna25" class="fn" href="#fn25" title="Gendron / Feldman Barrett 2009.">[25]</a> for a brief
209 computational analysis of emotions: Ekman’s <span style="color:#035151"><i>theory of basic 327 history of ideas about emotion in psychology. Here, we will focus on three
210 emotions</i></span>, Plutchik’s <span style="color:#035151"><i>wheel of emotion</i></span>, and Russel’s 328 views on emotion that are popular in computational analysis of emotions
211 <span style="color:#035151"><i>circumplex model</i></span>. 329 (though they are, from a psychological perspective, motivated from different
212 </p> 330 perspectives and represent different elements of affect and emotion):
213 <div id="subchapter"><a name="hd4"> </a><h3> 331 Ekman’s <span style="color:#035151"><i>theory of basic emotions</i></span>, Plutchik’s <span style="color:#035151"><i>wheel of emotion</i></span>, and Russel’s <span style="color:#035151"><i>circumplex model</i></span>.
332 </p><a name="div8"> </a><div id="subchapter"><a name="hd6"> </a><h3>
214 <div style="position:relative;width:90%;">2.1 Ekman’s Theory of Basic Emotions</div> 333 <div style="position:relative;width:90%;">2.1 Ekman’s Theory of Basic Emotions</div>
215 </h3> 334 </h3>
216 <p>The basic emotion theory was first articulated by Silvan Tomkins<a id="fna24" class="fn" href="#fn24" title="Tomkins 1962, passim.">[24]</a> in the early 1960s. Tomkins postulated that each instance 335 <p id="pid18"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid18">18</a>]</span>The idea of basic emotion theories is that there are emotions that are
217 of a certain emotion is biologically similar to other instances of the same emotion 336 more "fundamental" than others. Mixtures of emotions which receive a
218 or shares a common trigger. One of Tomkins’ mentees, Paul Ekman, put in question the 337 particular name are not necessarily defined as being basic. Attempts to
219 existing emotion theories that proclaimed that facial expressions of emotion are 338 find a definition for emotions date back to Silvan Tomkins<a id="fna26" class="fn" href="#fn26" title="Tomkins 1962.">[26]</a> in the early 1960s, who
220 socially learned and therefore vary from culture to culture. Ekman, Sorenson and 339 characterized emotions based on similarities of stimuli and biological
221 Friesen challenged this view<a id="fna25" class="fn" href="#fn25" title="Ekman et&nbsp;al. 1969, pp. 86-88.">[25]</a> 340 processes, following the ideas that have been described already by
222 in a field study with the outcome that facial displays of fundamental emotions are 341 Charles Darwin – clearly an attempt that focuses on observations and
223 not learned but innate. However, there are culture-specific prescriptions about how 342 evolution.
224 and in which situations emotions are displayed. 343 </p>
225 </p> 344 <p id="pid19"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid19">19</a>]</span>One of Tomkins’ mentees, Paul Ekman, put in question the existing emotion
226 <p>Based on the observation of facial behavior in early development or social 345 theories that proclaimed that facial expressions of emotion are socially
227 interaction, Ekman’s theory also postulates that emotions should be considered <span style="color:#035151"><i>discrete categories</i></span><a id="fna26" class="fn" href="#fn26" title="Ekman 1993, p. 386.">[26]</a> 346 learned and therefore vary from culture to culture. Ekman, Sorenson and
228 rather than continuous. Though this 347 Friesen challenged this view<a id="fna27" class="fn" href="#fn27" title="Ekman et al. 1969, pp. 86–88.">[27]</a> in a field study with the outcome that facial
229 view allows for conceiving of emotions as having different intensities, it does not 348 displays of fundamental emotions are not learned but innate. However,
230 allow emotions to blend and leaves no room for more complex affective states in which 349 there are culture-specific prescriptions about how and in which
231 individuals report the <span style="color:#035151"><i>co-occurrence of like-valenced discrete 350 situations emotions are displayed. Based on the observation of facial
232 emotions</i></span>.<a id="fna27" class="fn" href="#fn27" title="Feldman Barrett 1998, pp. 580f.">[27]</a> This and other theory 351 behavior in early development or social interaction, Ekman’s theory also
233 postulates were widely criticized and disputed in literature.<a id="fna28" class="fn" href="#fn28" title="Russell 1994; Russell et&nbsp;al. 2003; Gendron et&nbsp;al. 2014; Feldman Barrett 2017.">[28]</a></p> 352 postulates that emotions should be considered <span style="color:#035151"><i>discrete
234 </div> 353 categories</i></span><a id="fna28" class="fn" href="#fn28" title="Ekman 1993, p. 386.">[28]</a> rather than
235 <div id="subchapter"><a name="hd5"> </a><h3> 354 continuous. Though this view allows for conceiving of emotions as having
355 different intensities, it does not allow emotions to blend and leaves no
356 room for more complex affective states in which individuals report the
357 <span style="color:#035151"><i>co-occurrence of like-valenced discrete
358 emotions</i></span>.<a id="fna29" class="fn" href="#fn29" title="Russell 1994; Russell et al. 2003; Gendron et al. 2014; Feldman Barrett 2017.">[29]</a>.
359 </p>
360 <p id="pid20"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid20">20</a>]</span>Ekman and colleagues, however, defined clearly how basic emotions can be
361 distinguished from other emotions: There are distinctive universal
362 signals, the presence in other primates, distinctive phyiosology,
363 distinctive universals in antecedent events, coherence in the emotional
364 response, a quick onset, a brief duration, an automatic appraisal, and
365 an automatic, unbidden occurrence. The set
366 of emotions that is typically
367 referred to as "Ekman emotions" consists of anger, fear, joy, sadness,
368 surprise, and disgust. Given that this set of emotions is relevant for
369 many studies, and that these emotion categories do not deserve further
370 explanation to most people, it constitutes a popular basis for
371 computational analysis.
372 </p>
373 </div><a name="div9"> </a><div id="subchapter"><a name="hd7"> </a><h3>
236 <div style="position:relative;width:90%;">2.2 Plutchik’s Wheel of Emotions</div> 374 <div style="position:relative;width:90%;">2.2 Plutchik’s Wheel of Emotions</div>
237 </h3> 375 </h3>
238 <p>Another influential model of emotions was proposed by Robert Plutchik in the early 376 <p id="pid21"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid21">21</a>]</span>Another influential model of emotions was proposed by Robert Plutchik
239 1980s.<a id="fna29" class="fn" href="#fn29" title="Plutchik 1991, passim.">[29]</a> The important difference 377 in the early 1980s.<a id="fna30" class="fn" href="#fn30" title="Plutchik 1991.">[30]</a> The
240 between Plutchik’s theory and Ekman’s theory is that apart from a small set of basic 378 important difference between Plutchik’s theory and Ekman’s theory is
241 emotions, all other emotions are mixed and derived from the various combinations of 379 that apart from a small set of basic emotions, all other emotions
242 basic ones. He further categorized these other emotions into the <span style="color:#035151"><i>primary dyads</i></span> (very likely to co-occur), <span style="color:#035151"><i>secondary 380 are mixed and derived from the various
243 dyads</i></span> (less likely to co-occur) and <span style="color:#035151"><i>tertiary dyads</i></span> 381 combinations of basic ones.
244 (seldom co-occur). 382 He further categorized these other emotions into the <span style="color:#035151"><i>primary dyads</i></span> (very likely to co-occur), <span style="color:#035151"><i>secondary dyads</i></span> (less likely to co-occur) and <span style="color:#035151"><i>tertiary dyads</i></span> (seldom co-occur).
245 </p> 383 </p>
246 <p>In order to represent the organization and properties of emotions as defined by his 384 <p id="pid22"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid22">22</a>]</span>In order to represent the organization and properties of emotions as
247 theory, Plutchik proposed a structural model of emotions known nowadays as <i>Plutchik’s wheel of emotions</i>. The wheel <a title="" href="#emotion_analysis_2019_001"><span class="medium">Figure 1</span></a> is constructed in the fashion of a color wheel, with 385 defined by his theory, Plutchik proposed a structural model of
248 similar emotions placed closer together and opposite emotions 180 degrees apart. The 386 emotions known nowadays as <i>Plutchik’s wheel of emotions</i>. The wheel (<a title="" href="#emotion_analysis_2019_001"><span class="medium">Figure 1</span></a>) is constructed in the fashion of a color
249 intensity of an emotion in the wheel depends on how far from the center a part of 387 wheel, with similar emotions placed closer together and opposite
250 a 388 emotions 180 degrees apart. The intensity of an emotion in the wheel
251 petal is, i.e., emotions become less distinguishable the further they are from the 389 depends on how far from the center a part of a petal is, i.e.,
252 center of the wheel. Essentially, the wheel is constructed from eight basic bipolar 390 emotions become less distinguishable the further they are from the
253 emotions: <i>joy</i> versus <i>sorrow</i>, <i>anger</i> versus <i>fear</i>, <i>trust</i> versus <i>disgust</i>, and <i>surprise</i> versus <i>anticipation</i>. The blank spaces 391 center of the wheel. Essentially, the wheel is constructed from
254 between the leaves are so-called <span style="color:#035151"><i>primary dyads</i></span> – emotions that 392 eight basic bipolar emotions: <i>joy</i> versus <i>sadness</i>, <i>anger</i> versus
255 are mixtures of two of the primary emotions. 393 <i>fear</i>, <i>trust</i> versus
256 </p> 394 <i>disgust</i>, and <i>surprise</i> versus <i>anticipation</i>. The
257 <p>The <i>wheel model of emotions</i> proposed by Plutchik had a great impact on the field of affective computing 395 blank spaces between the leaves are so-called <span style="color:#035151"><i>primary dyads</i></span> – emotions that are mixtures of two of the
258 being primarily used as a basis for emotion categorization in emotion recognition 396 primary emotions.
259 from text.<a id="fna30" class="fn" href="#fn30" title="Cambria et&nbsp;al. 2012; Kim et&nbsp;al. 2012; Suttles / Ide 2013; Borth et&nbsp;al. 2013; Abdul-Mageed / Ungar 2017.">[30]</a> However, some postulates of the theory are criticized, 397 </p>
260 for example, there is no empirical support for the wheel structure.<a id="fna31" class="fn" href="#fn31" title="Smith / Schneider 2009, passim.">[31]</a> Another criticism is that 398 <p id="pid23"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid23">23</a>]</span>The <i>wheel model of emotions</i> proposed by Plutchik had a great impact on the field of
261 Plutchik’s model of emotion does not explain the mechanisms by which <i>love</i>, <i>hate</i>, <i>relief</i>, <i>pride</i>, and other everyday emotions emerge 399 affective computing being primarily used as a basis for emotion
262 from the <i>basic</i> emotions, nor does it provide reliable 400 categorization in emotion recognition from text.<a id="fna31" class="fn" href="#fn31" title="Cambria et al. 2012; Kim et al. 2012; Suttles / Ide 2013; Borth et al. 2013; Abdul-Mageed / Ungar 2017.">[31]</a>
263 measurements of these emotions.<a id="fna32" class="fn" href="#fn32" title="Richins 1997, p. 128.">[32]</a></p> 401 However, some postulates of the theory are criticized, for example,
402 there is no empirical support for the wheel structure.<a id="fna32" class="fn" href="#fn32" title="Smith / Schneider 2009.">[32]</a> Another
403 criticism is that Plutchik’s model of emotions does not explain the
404 mechanisms by which non-basic emotions emerge from the <i>basic</i> emotions, nor does it provide reliable
405 measurements of these emotions.<a id="fna33" class="fn" href="#fn33" title="Richins 1997, p. 128.">[33]</a></p>
264 <div class="medium"> 406 <div class="medium">
265 <div class="field-item even" rel="og:image rdfs:seeAlso" resource="../medium1"><a href="http://www.zfdg.de/sites/default/files/medien/emotion_analysis_2019_001.png" title="Fig. 1: Plutchik’s wheel of emotions. [Plutchik 2011. PD]" rel="gallery-node" class="colorbox"><img style="max-height:450px!important" class="artikel" alt="Fig. 1: Plutchik’s wheel of emotions. [Plutchik 2011. &#xA; PD]&#xA; " id="emotion_analysis_2019_001" src="http://www.zfdg.de/sites/default/files/styles/medium_in_artikel/emotion_analysis_2019_001.png"></a></div> 407 <div class="field-item even" rel="og:image rdfs:seeAlso" resource="../medium1"><a href="http://www.zfdg.de/sites/default/files/medien/emotion_analysis_2019_001.png" title="Fig. 1: Plutchik’s wheel of emotions. [Plutchik 2011. PD]" rel="gallery-node" class="colorbox"><img style="max-height:450px!important" class="artikel" alt="Fig. 1: Plutchik’s wheel of emotions. [Plutchik 2011.&#xA; PD] " id="emotion_analysis_2019_001" src="http://www.zfdg.de/sites/default/files/styles/medium_in_artikel/emotion_analysis_2019_001.png"></a></div>
266 <div class="img_desc"><a href="#abb1">Fig. 1</a>: Plutchik’s wheel of emotions. [<a href="#plutchik_wheel_2011">Plutchik 2011</a>. 408 <div class="img_desc"><a href="#abb1">Fig. 1</a>: Plutchik’s wheel of emotions. [<a href="#plutchik_wheel_2011">Plutchik 2011</a>.
267 <a href="https://creativecommons.org/publicdomain/mark/1.0/deed.de">PD</a>] 409 <a href="https://creativecommons.org/publicdomain/mark/1.0/deed.de">PD</a>] <a href="#emotion_analysis_2019_001"></a></div>
268 <a href="#emotion_analysis_2019_001"></a></div> 410 </div>
269 </div> 411 </div><a name="div10"> </a><div id="subchapter"><a name="hd8"> </a><h3>
270 </div>
271 <div id="subchapter"><a name="hd6"> </a><h3>
272 <div style="position:relative;width:90%;">2.3 Russel’s Circumplex Model</div> 412 <div style="position:relative;width:90%;">2.3 Russel’s Circumplex Model </div>
273 </h3> 413 </h3>
274 <p>Attempts to overcome the shortcomings of basic emotions theory and its unfitness for 414 <p id="pid24"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid24">24</a>]</span>Attempts to overcome the shortcomings of basic emotion theories
275 clinical studies led researchers to suggest various dimensional models, the most 415 and its unfitness for clinical studies led researchers to
276 prominent of which is the circumplex model of affect proposed by James Russel.<a id="fna33" class="fn" href="#fn33" title="Russell 1980.">[33]</a> The word <span style="color:#035151"><i>circumplex</i></span> 416 suggest various dimensional models, the most prominent of which
277 in the name of the model refers to the fact that emotional episodes do not cluster 417 is the circumplex model of affect proposed by James Russel.<a id="fna34" class="fn" href="#fn34" title="Russell 1980.">[34]</a> The word <span style="color:#035151"><i>circumplex</i></span> in the name of the model refers
278 at 418 to the fact that emotional episodes do not cluster at the axes
279 the axes but rather at the periphery of a circle <a title="" href="#emotion_analysis_2019_002"><span class="medium">Figure 2</span></a>. At the core of the 419 but rather at the periphery of a circle (<a title="" href="#emotion_analysis_2019_002"><span class="medium">Figure 2</span></a>). At the core of
280 circumplex model is the notion of two dimensions plotted on a circle along horizontal 420 the circumplex model is the notion of two dimensions plotted on
281 and vertical axes. These dimensions are <i>valence</i> (how pleasant 421 a circle along horizontal and vertical axes. These dimensions
282 or unpleasant one feels) and <i>arousal</i> (the degree of calmness 422 are <i>valence</i> (how pleasant or unpleasant
283 or excitement). The number of dimensions is not strictly fixed and there are 423 one feels) and <i>arousal</i> (the degree of
284 adaptations of the model that incorporate more dimensions. One example of this is 424 calmness or excitement). The number of dimensions is not
285 the 425 strictly fixed and there are adaptations of the model that
286 <span style="color:#035151"><i>Valence-Arousal-Dominance model </i></span>that adds an additional 426 incorporate more dimensions. One example of this is the <span style="color:#035151"><i>Valence-Arousal-Dominance model </i></span>that adds
287 dimension of dominance, the degree of control one feels over the situation that 427 an additional dimension of dominance, the degree of control one
288 causes an emotion.<a id="fna34" class="fn" href="#fn34" title="Bradley / Lang 1994, p. 50.">[34]</a></p> 428 feels over the situation that causes an emotion.<a id="fna35" class="fn" href="#fn35" title="Bradley / Lang 1994, p. 50.">[35]</a></p>
289 <p>By moving from discrete categories to a dimensional representation, the researchers 429 <p id="pid25"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid25">25</a>]</span>By moving from discrete categories to a dimensional
290 are able to account for subjective experiences that do not fit nicely into the 430 representation, the researchers are able to account for
291 isolated non-overlapping categories. Accordingly, each affective experience can be 431 subjective experiences that do not fit nicely into the isolated
292 depicted as a point in a <i>circumplex</i> that is described by only 432 non-overlapping categories. Accordingly, each affective
293 two parameters – <i>valence</i> and <i>arousal</i> – 433 experience can be depicted as a point in a <i>circumplex</i> that is described by only two parameters –
294 without need for labeling or reference to emotion concepts for which a name might 434 <i>valence</i> and <i>arousal</i> – without need for labeling or reference to
295 only exist in particular subcommunities or which are difficult to describe.<a id="fna35" class="fn" href="#fn35" title="Russell 2003, p. 154.">[35]</a> However, the strengths of the model turned 435 emotion concepts for which a name might only exist in particular
296 out to be its weaknesses: for example, it is not clear whether there are basic 436 subcommunities or which are difficult to describe.<a id="fna36" class="fn" href="#fn36" title="Russell 2003, p. 154.">[36]</a>
297 dimensions in the model<a id="fna36" class="fn" href="#fn36" title="Larsen / Diener 1992, p. 25.">[36]</a> nor is it 437 However, the
298 clear what should be done with qualitatively different events of <i>fear</i>, <i>anger</i>, <i>embarrassment</i> and 438 strengths of the model turned out to be its weaknesses: for
299 <i>disgust</i> that fall in identical places in the circumplex 439 example, it is not clear whether there are basic dimensions in
300 structure.<a id="fna37" class="fn" href="#fn37" title="Russell / Feldman Barrett 1999, p. 807.">[37]</a> Despite these 440 the model<a id="fna37" class="fn" href="#fn37" title="Larsen / Diener 1992, p. 25.">[37]</a> nor is it clear what should be done with
301 shortcomings, the circumplex model of affect is widely used in psychologic and 441 qualitatively different events of <i>fear</i>,
302 psycholinguistic studies. In computational linguistics, the circumplex model is 442 <i>anger</i>, <i>embarrassment</i> and <i>disgust</i> that
303 applied when the interest is in continuous measurements of <i>valence</i> and <i>arousal</i> rather than in the specific 443 fall in identical places in the circumplex structure.<a id="fna38" class="fn" href="#fn38" title="Russell / Feldman Barrett 1999, p. 807.">[38]</a>
444 Despite these shortcomings, the circumplex model of affect is
445 popular in psychologic and psycholinguistic studies, because
446 both dimensions can reliably be measured.<a id="fna39" class="fn" href="#fn39" title="Mauss / Robinson 2009.">[39]</a> In computational linguistics,
447 the circumplex model is applied when the interest is in
448 continuous measurements of <i>valence</i> and
449 <i>arousal</i> rather than in the specific
304 discrete emotional categories. 450 discrete emotional categories.
305 </p> 451 </p>
452 <p id="pid26"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid26">26</a>]</span>There are other models which locate discrete emotion categories
453 in a dimensional space, however, these have not been used in
454 computational literary studies yet (though such approaches are
455 promising also in this domain and constitute promising future
456 research). One instance, next to valence/arousal, are appraisal
457 theories<a id="fna40" class="fn" href="#fn40" title="Scherer 2005.">[40]</a> which
458 state that different dimensions, which measure how a stimulus
459 event is cognitively evaluated enable different sets of
460 emotions. The work by Smith and Ellsworth<a id="fna41" class="fn" href="#fn41" title="Smith / Ellsworth 1985.">[41]</a> shows that the six dimensions
461 of (1) how pleasant an event is, (2) how much effort an event
462 can be expected to cause, (3) how certain the experiencer is in
463 a specific situation, (4) how much attention is devoted to the
464 event, (5) how much responsibility the experiencer of the
465 emotion holds for what has happened, and (6) how much the
466 experiencer has control over the situation, explain 15 discrete
467 emotions.
468 </p>
306 <div class="medium"> 469 <div class="medium">
307 <div class="field-item even" rel="og:image rdfs:seeAlso" resource="../medium1"><a href="http://www.zfdg.de/sites/default/files/medien/emotion_analysis_2019_002.png" title="Fig. 2: Circumplex model of affect: Horizontal axis represents the valence dimension, the vertical axis represents the arousal dimension. Drawn after Posner et al. 2005. [Kim / Klinger 2019]" rel="gallery-node" class="colorbox"><img style="max-height:450px!important" class="artikel" alt="Fig. 2: Circumplex model of affect: Horizontal axis represents the valence dimension, &#xA; the vertical axis represents the arousal dimension. Drawn after Posner et al. 2005. [Kim / Klinger 2019]" id="emotion_analysis_2019_002" src="http://www.zfdg.de/sites/default/files/styles/medium_in_artikel/emotion_analysis_2019_002.png"></a></div> 470 <div class="field-item even" rel="og:image rdfs:seeAlso" resource="../medium1"><a href="http://www.zfdg.de/sites/default/files/medien/emotion_analysis_2019_002.png" title="Fig. 2: Circumplex model of affect: Horizontal axis represents the valence dimension, the vertical axis represents the arousal dimension. Drawn after Posner et al. 2005. [Kim / Klinger 2019]" rel="gallery-node" class="colorbox"><img style="max-height:450px!important" class="artikel" alt="Fig. 2: Circumplex model of affect: Horizontal&#xA; axis represents the valence dimension, the vertical axis represents the&#xA; arousal dimension. Drawn after Posner et al. 2005. [Kim / Klinger&#xA; 2019]" id="emotion_analysis_2019_002" src="http://www.zfdg.de/sites/default/files/styles/medium_in_artikel/emotion_analysis_2019_002.png"></a></div>
308 <div class="img_desc"><a href="#abb2">Fig. 2</a>: Circumplex model of affect: Horizontal axis represents the valence dimension, 471 <div class="img_desc"><a href="#abb2">Fig. 2</a>: Circumplex model of affect: Horizontal
309 the vertical axis represents the arousal dimension. Drawn after <a href="#posner_model_2005">Posner et al. 2005</a>. [Kim / Klinger 2019]<a href="#emotion_analysis_2019_002"></a></div> 472 axis represents the valence dimension, the vertical axis represents the
310 </div> 473 arousal dimension. Drawn after <a href="#posner_model_2005">Posner et al. 2005</a>. [Kim / Klinger
311 </div> 474 2019]<a href="#emotion_analysis_2019_002"></a></div>
312 </div> 475 </div>
313 <div id="chapter"><a name="hd7"> </a><h2> 476 </div>
477 </div><a name="div11"> </a><div id="chapter"><a name="hd9"> </a><h2>
314 <div style="position:relative;width:90%;">3 Emotion Analysis in Non-computational Literary Studies</div> 478 <div style="position:relative;width:90%;">3 Emotion Analysis in Non-computational Literary Studies</div>
315 </h2> 479 </h2>
316 <p>Until the end of the twentieth century, literary and art theories often disregarded 480 <p id="pid27"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid27">27</a>]</span>In the past, literary and art theories often disregarded the importance of
317 the importance of the aesthetic and affective dimension of literature, which in part 481 the aesthetic and affective dimension of literature, which in part stemmed
318 stemmed from the rejection of old-fashioned literary history that had explained the 482 from the rejection of old-fashioned literary history that had explained the
319 meaning of art works by the biography of the author.<a id="fna38" class="fn" href="#fn38" title="Sætre et&nbsp;al. 2014b, passim.">[38]</a> However, the affective turn taken by a wide range of 483 meaning of art works by the biography of the author.<a id="fna42" class="fn" href="#fn42" title="Sætre et&nbsp;al. 2014b.">[42]</a> However, the affective turn taken by a wide
320 disciplines in the past two decades – from political and sociological sciences to 484 range of disciplines in the past two decades – from political and
321 neurosciences or media studies – has refueled the interest of literary critics in 485 sociological sciences to neurosciences or media studies – has refueled the
322 human affects and sentiments. 486 interest of literary critics in human affects and sentiments.
323 </p> 487 </p>
324 <p>We said in <a title="" href="#hd1">Section 1</a> that there seems to be a consensus among literary critics that 488 <p id="pid28"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid28">28</a>]</span>We said in <a title="" href="#hd1">section 1</a> that there seems
325 literary art and emotions go hand in hand. However, one might be challenged to define 489 to be a consensus among literary critics that literary art and emotions go
326 the specific way in which emotions come into play in the text. The exploration of 490 hand in hand. However, one might be challenged to define the specific way in
327 this problem is presented by van Meel.<a id="fna39" class="fn" href="#fn39" title="Van Meel 1995, passim.">[39]</a> 491 which emotions come into play in the text. The exploration of this problem
328 Underpinning the centrality of human destiny, hopes, and feelings in the themes of 492 is presented by van Meel.<a id="fna43" class="fn" href="#fn43" title="Van Meel 1995.">[43]</a>
329 many artworks – from painting to literature – van Meel explores how emotions are 493 Underpinning the centrality of human destiny, hopes, and feelings in the
330 involved in the production of arts. Pointing out big differences between the two 494 themes of many artworks – from painting to literature – van Meel explores
331 media in their attempts to depict human emotions (painting conveys nonverbal behavior 495 how emotions are involved in the production of arts. Pointing out big
332 directly, but lacks temporal dimensions that novels have and use to describe 496 differences between the two media in their attempts to depict human emotions
333 emotions), van Meel provides an analysis of the nonverbal descriptions used by the 497 (painting conveys nonverbal behavior directly, but lacks temporal dimensions
334 writers to convey their characters’ emotional behavior. Description of visual 498 that novels have and use to describe emotions), van Meel provides an
335 characteristics, van Meel speculates, responds to a fundamental need of a reader to 499 analysis of the nonverbal descriptions used by the writers to convey their
336 build an image of a person and their behavior. Moreover, nonverbal descriptions add 500 characters’ emotional behavior. Description of visual characteristics, van
337 important information that can in some cases play a crucial hermeneutical role, such 501 Meel speculates, responds to a fundamental need of a reader to build an
338 as in Kafka’s <i>Der Prozess</i>, where the fatal decisions for K. are made clear by gestures rather than 502 image of a person and their behavior. Moreover, nonverbal descriptions add
339 words. His verdict is not announced, but is implied by the judge who refuses a 503 important information that can in some cases play a crucial hermeneutical
340 handshake. The same applies to his death sentence that is conveyed to him by his 504 role, such as in Kafka’s <i>Der Prozess</i>, where the fatal decisions for K. are made clear by gestures rather
341 executioners playing with a butcher’s knife above his head. 505 than words. His verdict is not announced, but is implied by the judge who
342 </p> 506 refuses a handshake. The same applies to his death sentence that is conveyed
343 <p>A hermeneutic approach through the lense of emotions is presented by Kuivalainen<a id="fna40" class="fn" href="#fn40" title="Kuivalainen 2009, passim.">[40]</a> and provides a detailed analysis of 507 to him by his executioners playing with a butcher’s knife above his head.
344 linguistic features that contribute to the characters’ emotional involvement in 508 These aspects how emotions are communicated clearly point to challenges for
345 Mansfield’s prose. The study shows how, through the extensive use of adjectives, 509 computational methods – implicit descriptions, world knowledge, and
346 adverbs, deictic markers, and orthography, Mansfield steers the reader towards the 510 inference steps that are grounded in combinations of text and readers'
347 protagonist’s climax. Subtly shifting between psycho-narration and free indirect 511 experiences have not been tackled with computational methods yet.
348 discourse, Mansfield is making use of evaluative and emotive descriptors in 512 </p>
349 psycho-narrative sections, often marking the internal discourse with dashes, 513 <p id="pid29"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid29">29</a>]</span>A hermeneutic approach through the lense of emotions is presented by
350 exclamation marks, intensifiers, and repetition that thus trigger an emotional 514 Kuivalainen<a id="fna44" class="fn" href="#fn44" title="Kuivalainen 2009.">[44]</a> and provides
351 climax. Various deictic features introduced in the text are used to pinpoint the 515 a detailed analysis of linguistic features that contribute to the
352 source of emotions, which helps in creating a picture of characters’ emotional world. 516 characters’ emotional involvement in Katherine Mansfield’s prose. The study
353 Verbs (especially in the present tense), adjectives, and adverbs serve the same goal 517 shows how, through the extensive use of adjectives, adverbs, deictic
354 in Mansfield’s prose of describing the characters’ emotional world. Going back and 518 markers, and orthography, Mansfield steers the reader towards the
355 forth from psycho-narration to free indirect discourse provides Mansfield with a tool 519 protagonist’s climax. Subtly shifting between psycho-narration and free
356 to point out the significant moments in the protagonists’ lives and establish a 520 indirect discourse, Mansfield is making use of evaluative and emotive
357 separation between characters and narration. 521 descriptors in psycho-narrative sections, often marking the internal
358 </p> 522 discourse with dashes, exclamation marks, intensifiers, and repetition that
359 <p>Both van Meel’s and Kuivalainen’s works, separated from each other by more than a 523 thus trigger an emotional climax. Various deictic features introduced in the
360 decade, underpin the importance of emotions in the interpretation of characters’ 524 text are used to pinpoint the source of emotions, which helps in creating a
361 traits, hopes, and tragedy. Other authors find these connections as well. For 525 picture of characters’ emotional world. Verbs (especially in the present
362 example, Barton<a id="fna41" class="fn" href="#fn41" title="Barton 1996, passim.">[41]</a> proposes instructional 526 tense), adjectives, and adverbs serve the same goal in Mansfield’s prose of
363 approaches to teach school-level readers to interpret character’s emotions and use 527 describing the characters’ emotional world. Going back and forth from
364 this information for story interpretation. Van Horn<a id="fna42" class="fn" href="#fn42" title="Van&nbsp;Horn 1997, passim.">[42]</a> shows that understanding characters emotionally or trying to help 528 psycho-narration to free indirect discourse provides Mansfield with a tool
365 them with their problems made reading and writing more meaningful for middle school 529 to point out the significant moments in the protagonists’ lives and
530 establish a separation between characters and narration. This study
531 illustrates another challenge for automatic methods. Computational models
532 mostly rely on isolated, comparable short, units of the text. The broader
533 context, let alone the development of characters, are mostly ignored in
534 computational analysis – a prediction depends on the local description and
535 is not conditioned on previous experiences. That is a clear disadvantage of
536 distant reading methods to close reading.
537 </p>
538 <p id="pid30"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid30">30</a>]</span>Both van Meel’s and Kuivalainen’s works, separated from each other by more
539 than a decade, underpin the importance of emotions in the interpretation of
540 characters’ traits, hopes, and tragedy. Other authors find these connections
541 as well. For example, Barton<a id="fna45" class="fn" href="#fn45" title="Barton 1996.">[45]</a>
542 proposes instructional approaches to teach school-level readers to interpret
543 character’s emotions and use this information for story interpretation. Van
544 Horn<a id="fna46" class="fn" href="#fn46" title="Van&nbsp;Horn 1997.">[46]</a> shows that
545 understanding characters emotionally or trying to help them with their
546 problems made reading and writing more meaningful for middle school
366 students. 547 students.
367 </p> 548 </p>
368 <p>Emotions in text are often conveyed with emotion-bearing words.<a id="fna43" class="fn" href="#fn43" title="Johnson-Laird / Oatley 1989, passim.">[43]</a> At the same time their role in the creation 549 <p id="pid31"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid31">31</a>]</span>Emotions in text are often conveyed with emotion-bearing words.<a id="fna47" class="fn" href="#fn47" title="Johnson-Laird / Oatley 1989.">[47]</a> At the same time
369 and depiction of emotion should not be overestimated. That is, saying that someone 550 their role in the creation and depiction of emotion should not be
370 looked angry or fearful or sad, as well as directly expressing characters’ emotions, 551 overestimated. That is, saying that someone looked angry or fearful or sad,
371 are not the only ways authors build believable fictional spaces filled with 552 as well as directly expressing characters’ emotions, are not the only ways
372 characters, action, and emotions. In fact, many novelists strive to express emotions 553 authors build believable fictional spaces filled with characters, action,
373 indirectly by way of figures of speech or catachresis,<a id="fna44" class="fn" href="#fn44" title="Miller 2014, p. 92.">[44]</a> first of all because emotional language can be 554 and emotions. In fact, many novelists strive to express emotions indirectly
374 ambiguous and vague, and, second, to avoid any allusions to Victorian emotionalism 555 by way of figures of speech or catachresis,<a id="fna48" class="fn" href="#fn48" title="Miller 2014, p. 92.">[48]</a> first of all because emotional language can be
375 and pathos. 556 ambiguous and vague, and, second, to avoid any allusions to Victorian
376 </p> 557 emotionalism and pathos.
377 <p>How can an author convey emotions indirectly? A book chapter by Hillis Miller in <i>Exploring Text and Emotions</i><a id="fna45" class="fn" href="#fn45" title="Sætre et&nbsp;al. 2014a, p. 91ff.">[45]</a> seeks the answer to exactly this 558 </p>
378 question. Using Conrad’s <i>Nostromo</i> opening scenes as material, Hillis Miller shows how Conrad’s descriptions of 559 <p id="pid32"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid32">32</a>]</span>How can an author convey emotions indirectly? A book chapter by Hillis Miller
379 an imaginary space generate emotions in readers without direct communication of 560 in <i>Exploring Text and Emotions</i><a id="fna49" class="fn" href="#fn49" title="Sætre et&nbsp;al. 2014a, pp. 91ff.">[49]</a> seeks the answer
380 emotions. Conrad’s <i>Nostromo</i> opening chapter is an objective description of Sulaco, an imaginary land. The 561 to exactly this question. Using Joseph Conrad’s <i>Nostromo</i> opening scenes as material, Miller shows how Conrad’s descriptions
381 description is mainly topographical and includes occasional architectural metaphors, 562 of an imaginary space generate emotions in readers without direct
382 but it combines wide expanse with hermetically sealed enclosure, which generates 563 communication of emotions. Conrad’s <i>Nostromo</i> opening chapter is an objective description of Sulaco, an imaginary
383 depthless emotional detachment<a id="fna46" class="fn" href="#fn46" title="Miller 2014, p. 93.">[46]</a>. Through the use of present tense, Conrad makes the readers suggest 564 land. The description is mainly topographical and includes occasional
384 that the whole scene is timeless and does not change. The topographical descriptions 565 architectural metaphors, but it combines wide expanse with hermetically
385 are given in a pure materialist way: there is nothing behind clouds, mountains, 566 sealed enclosure, which generates »depthless emotional
386 rocks, and sea that would matter to humankind, not a single feature of the landscape 567 detachment«<a id="fna50" class="fn" href="#fn50" title="Miller 2014, p. 93.">[50]</a>. Through the use of
387 is personified, and not a single topographical shape is symbolic. Knowingly or 568 present tense, Conrad makes the readers suggest that the whole scene is
388 unknowingly, Miller argues, by telling the readers what they should see – with no 569 timeless and does not change. The topographical descriptions are given in a
389 deviations from truth – Conrad employs a trope that perfectly matches Kant’s <i>concept of the sublime</i>. Kant’s view of poetry was that true poets tell the truth without 570 pure materialist way: there is nothing behind clouds, mountains, rocks, and
390 interpretation; they do not deviate from what their eyes see. Conrad, or to be more 571 sea that would matter to humankind, not a single feature of the landscape is
391 specific, his narrator in <i>Nostromo</i>, is an example of sublime seeing with a latent presence of strong emotions. 572 personified, and not a single topographical shape is symbolic. Knowingly or
392 On the one hand, Conrad’s descriptions are cool and detached. This coolness is caused 573 unknowingly, Miller argues, by telling the readers what they should see –
393 by the indifference of the elements in the scene. On the other hand, by dehumanizing 574 with no deviations from truth – Conrad employs a trope that perfectly
394 sea and sky, Conrad generates awe, fear, and a dark foreboding about the kinds of 575 matches Immanuel Kant’s <i>concept of the sublime</i>. Kant’s view of poetry was that true poets tell the truth without
395 life stories that are likely to be enacted against such a backdrop<a id="fna47" class="fn" href="#fn47" title="Miller 2014, p. 115.">[47]</a>. 576 interpretation; they do not deviate from what their eyes see. Conrad, or to
396 </p> 577 be more specific, his narrator in <i>Nostromo</i>, is an example of sublime seeing with a latent presence of strong
397 <p>Hillis Miller’s analysis resonates with some premises from emotion theory that we 578 emotions. On the one hand, Conrad’s descriptions are cool and detached. This
398 have discussed previously, namely, Plutchik’s belief that emotions should be studied 579 coolness is caused by the indifference of the elements in the scene. On the
399 not by a certain way of expression but by the overall behavior of a person. 580 other hand, by dehumanizing sea and sky, Conrad generates »awe, fear,
400 Considering that such a formula cannot be applied to all literary theory studies 581 and a dark foreboding about the kinds of life stories that are likely to
401 about emotions (as not all authors choose to convey emotions indirectly, as well as 582 be enacted against such a backdrop.«<a id="fna51" class="fn" href="#fn51" title="Miller 2014, p. 115.">[51]</a></p>
402 not all authors tend to comment on characters’ nonverbal emotional behavior), it 583 <p id="pid33"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid33">33</a>]</span>Hillis Miller’s analysis resonates with some premises from emotion theory
403 seems that one should search for a balance between low-level linguistic feature 584 that we have discussed previously, namely, Plutchik’s belief that emotions
404 analysis of emotional language and a rigorous high-level hermeneutic inquiry 585 should be studied not by a certain way of expression but by the overall
405 dissecting the form of the novel and its under-covered philosophical layers. 586 behavior of a person. Considering that such a formula cannot be applied to
406 </p> 587 all literary theory studies about emotions (as not all authors choose to
407 </div> 588 convey emotions indirectly, as well as not all authors tend to comment on
408 <div id="chapter"><a name="hd8"> </a><h2> 589 characters’ nonverbal emotional behavior), it seems that one should search
590 for a balance between low-level linguistic feature analysis of emotional
591 language and a rigorous high-level hermeneutic inquiry dissecting the form
592 of the novel and its under-covered philosophical layers.<a id="fna52" class="fn" href="#fn52" title="We recommend the essay by Katja Mellmann for further details on that topic. Mellmann 2002.">[52]</a></p>
593 </div><a name="div12"> </a><div id="chapter"><a name="hd10"> </a><h2>
409 <div style="position:relative;width:90%;">4 Emotion and Sentiment Analysis in Computational Literary Studies</div> 594 <div style="position:relative;width:90%;">4 Emotion and Sentiment Analysis in Computational Literary Studies</div>
410 </h2> 595 </h2>
411 <p>With this section, we proceed to an overview of the existing body of research on 596 <p id="pid34"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid34">34</a>]</span>With this section, we proceed to an overview of the existing body of research
412 computational analysis of emotion and sentiment in computational literary studies. 597 on computational analysis of emotion and sentiment in computational literary
413 An 598 studies. An overview of the papers including their properties is shown in
414 overview of the papers including their properties is shown in 599 <a title="" href="#emotion_analysis_2019_003"><span class="medium">Table&nbsp;1</span></a>. The table,
415 <a title="" href="#emotion_analysis_2019_003"><span class="medium">Table&nbsp;1</span></a>. The table, as 600 as well as this section, is divided into several subsections, each of which
416 well as this section, is divided into several subsections, each of which corresponds 601 corresponds to a specific application of emotion analysis to literature.
417 to a specific application of emotion and sentiment analysis to literature. 602 <a title="" href="#hd11">section 4.1</a> reviews the papers
418 <a title="" href="#hd9">Section 4.1</a> reviews the papers that deal with the classification of literary texts in terms 603 that deal with the classification of literary texts in terms of emotions
419 of emotions they convey; <a title="" href="#hd12">Section 4.2</a> examines the papers that address text 604 they convey; <a title="" href="#hd14">section 4.2</a> examines the
420 classification by genre or other story-types based on sentiment and emotion features; 605 papers that address text classification by genre or other story-types based
421 <a title="" href="#hd15">Section 4.3</a> is dedicated to research in modeling sentiments and emotions in texts 606 on sentiment and emotion features; <a title="" href="#hd17">section
422 from previous centuries, as well as research dealing with applications of sentiment 607 4.3</a> is dedicated to research in modeling sentiments and emotions
423 analysis to texts written in the past; <a title="" href="#hd19">Section 4.4</a> provides an overview of sentiment 608 in texts from previous centuries, as well as research dealing with
424 analysis applications to character analysis and character network construction, and 609 applications of sentiment analysis to texts written in the past; <a title="" href="#hd21">section 4.4</a> provides an overview of
425 <a title="" href="#hd22">Section 4.5</a> is dedicated to more general applications of sentiment and emotion 610 sentiment analysis applications to character analysis and character network
426 analysis to literature. 611 construction, and <a title="" href="#hd24">section 4.5 </a>is
427 </p> 612 dedicated to more general applications.
428 <div id="subchapter"><a name="hd9"> </a><h3> 613 </p><a name="div13"> </a><div id="subchapter"><a name="hd11"> </a><h3>
429 <div style="position:relative;width:90%;">4.1 Emotion Classification</div> 614 <div style="position:relative;width:90%;">4.1 Emotion Classification</div>
430 </h3> 615 </h3>
431 <p>A straightforward approach to sentiment and emotion analysis is phrasing them as a 616 <p id="pid35"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid35">35</a>]</span>A straightforward approach to emotion analysis is text
432 text classification<a id="fna48" class="fn" href="#fn48" title="Liu 2015, p. 47.">[48]</a>. A fundamental 617 classification<a id="fna53" class="fn" href="#fn53" title="Liu 2015, p. 47.">[53]</a>.
433 question of such a classification is how to find the best features and algorithms 618 Indeed, emotion classification is one of the most popular subtasks and
434 to 619 finds application in several downstream tasks. A fundamental question of
435 classify the data (sentences, paragraphs, entire documents) into predefined classes. 620 such a classification is how to find the best input representations and
436 When applied to literature, such a classification may be of use for grouping 621 algorithms to classify the data (sentences, paragraphs, entire
437 different literary texts in digital collections based on the emotional properties 622 documents) into predefined classes. When applied to literature, such a
438 of 623 classification may be of use for grouping different literary texts in
439 the stories. For example, books or poems can be grouped based on the emotions they 624 digital collections based on the emotional properties of the stories or
440 convey or based on whether or not they have happy endings or not. 625 to perform other analyses regarding the distribution of emotions in
441 </p> 626 subcollections. For example, books or poems can be grouped based on the
442 <div id="subchapter"><a name="hd10"> </a><h3> 627 emotions they convey or based on whether or not they have happy endings
628 or not.
629 </p><a name="div14"> </a><div id="subchapter"><a name="hd12"> </a><h3>
443 <div style="position:relative;width:90%;">4.1.1 Classification based on emotions</div> 630 <div style="position:relative;width:90%;">4.1.1 Classification based on emotions</div>
444 </h3> 631 </h3>
445 <p>Barros et al.<a id="fna49" class="fn" href="#fn49" title="Barros et&nbsp;al. 2013, passim.">[49]</a> aim at answering two 632 <p id="pid36"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid36">36</a>]</span>Barros et al.<a id="fna54" class="fn" href="#fn54" title="Barros et&nbsp;al. 2013.">[54]</a> aim at
446 research questions: 1)&nbsp;is the classification of Quevedo’s works proposed by the 633 answering two research questions: 1)&nbsp;is the classification of
447 literary scholars consistent with the sentiment reflected by the corresponding 634 Francisco de Quevedo’s works proposed by the literary scholars
448 poems?; and 2)&nbsp;which learning algorithms are the best for the classification? To that 635 consistent with the sentiment reflected by the corresponding poems;
449 end, they perform a set of experiments on the classification of 185 Francisco de 636 and 2)&nbsp;which learning algorithms are the best for the classification
450 Quevedo’s poems that are divided by literary scholars into four categories and that 637 (the latter being an engineering question that is inherent in many
451 Barros et al. map to emotions of <i>joy</i>, <i>anger</i>, <i>fear</i>, and <i>sadness</i>. 638 of the papers that we discuss)? They perform a set of experiments on
452 Using the terms <i>joy</i>, <i>anger</i>, <i>fear</i>, and <i>sadness</i> as points of 639 the classification of 185 Francisco de Quevedo’s poems that are
453 reference, Barros et al. construct a list of emotion words by looking up the synonyms 640 divided by literary scholars into four categories and that Barros et
454 of English emotion words and adjectives associated with these four emotions and 641 al. map to emotions. Using the terms <i>joy</i>, <i>anger</i>, <i>fear</i>, and <i>sadness</i> as points of reference, Barros et al.
455 translating them into Spanish. Each poem is converted into a vector where each item 642 construct a list of emotion words by looking up the synonyms of
456 is a normalized count of words relating to a certain emotion. The experiments with 643 English emotion words and adjectives associated with these four
457 different algorithms show the superiority of decision trees achieving accuracy of 644 emotions and translating them into Spanish. This leads to a novel
458 almost 60%. However, this result is biased by an unbalanced distribution of classes. 645 and task-specific lexicon, to which each poem is then compared,
459 To avoid the bias, Barros et al. apply a resampling strategy that leads to a more 646 based on normalized term counts. The experiments show the
460 balanced distribution and repeat the classification experiments. After resampling, 647 superiority of decision trees as classification approach which can
461 the accuracy of decision trees in a 10-fold cross validation achieves 75,13%, thus 648 further be improved by rebalancing the collection via resampling.
462 demonstrating an improvement over the previous classification performance. Based on 649 Based on these results the authors conclude that a meaningful
463 these results the authors conclude that a meaningful classification of the literary 650 classification of the literary pieces based only on the emotion
464 pieces based only on the emotion information is possible. 651 information is possible.
465 </p> 652 </p>
466 <p>Reed<a id="fna50" class="fn" href="#fn50" title="Reed 2018, passim.">[50]</a> offers a <span style="color:#035151"><i>proof-of-concept</i></span> for performing sentiment analysis on a corpus of 653 <p id="pid37"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid37">37</a>]</span>A more modern corpus selection of poetry is the object of analysis by
467 twentieth-century American poetry. Specifically, Reed analyzes the expression of 654 Ethan Reed.<a id="fna55" class="fn" href="#fn55" title="Reed 2018">[55]</a>. The author
468 emotions in the poetry of the <span style="color:#035151"><i>Black Arts Movement</i></span> of the 1960s 655 offers a <span style="color:#035151"><i>proof-of-concept</i></span> for performing
469 and 1970s. The paper describes the project Measured Unrest in the Poetry of the Black 656 sentiment analysis on twentieth-century American poetry with
470 Arts Movement whose goal is to understand 1) how the feelings associated with 657 dictionary-based black-box sentiment analysis systems that output
471 injustice are coded in terms of race and gender, and 2) what sentiment analysis can 658 the polarity of a text. Specifically, they analyze the expression of
472 show us about the relations between affect and gender in poetry. Reed notes that 659 emotions in the poetry of the <span style="color:#035151"><i>Black Arts
473 surface affective value of the words does not always align with their more nuanced 660 Movement</i></span> of the 1960s and 1970s. The goal of the project
474 affective meaning shaped by poetic, social, and political contexts. 661 is to understand how feelings associated with injustice are coded in
475 </p> 662 terms of race and gender, and what sentiment analysis can show us
476 <p>Yu<a id="fna51" class="fn" href="#fn51" title="Yu 2008, passim.">[51]</a> explores what linguistic patterns 663 about the relations between affect and gender in poetry. Reed notes
477 characterize the genre of sentimentalism in early American novels. To that end, they 664 that the surface affective value of the words does not always align
478 construct a collection of five novels from the mid-nineteenth century and annotate 665 with their more nuanced affective meaning shaped by poetic, social,
479 the emotionality of each of the chapters as <i>high</i> or <i>low</i>. The respective chapters are then classified using 666 and political contexts. Therefore, this study can be seen as a
480 support-vector machines and naïve Bayes classifiers as highly emotional or the 667 critical reflection on methodological choices.
481 opposite. The results of the evaluation suggest that arbitrary feature reduction 668 </p>
482 steps such as stemming and stopword removal should be taken very carefully, as they 669 <p id="pid38"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid38">38</a>]</span>Yu<a id="fna56" class="fn" href="#fn56" title="Yu 2008.">[56]</a> explores linguistic patterns
483 may affect the prediction. For example, Yu shows that no stemming leads to better 670 that characterize the genre of sentimentalism in early American
484 classification results. A possible explanation is that stemming conflates and 671 novels. They analyze five novels from the mid-nineteenth century and
485 neutralizes a large number of discriminative features. The author provides an example 672 annotate the emotionality of each of the chapters as <i>high</i> or <i>low (not: positive
486 of such a conflation with the words <i>wilderness</i> and <i>wild</i>. While the latter can appear anywhere in the text, the 673 or negative!)</i>. This approach is noteworthy, as the unit of
487 former one is primarily encountered in the chapters filled with emotions. 674 analysis is comparably large in contrast to most sentiment analysis
488 </p> 675 methods. Each chapter is classified with standard configurations of
489 </div> 676 support vector machines and naïve Bayes classifiers, as highly
490 <div id="subchapter"><a name="hd11"> </a><h3> 677 emotional or the opposite. The results of the evaluation suggest
491 <div style="position:relative;width:90%;">4.1.2 Classification of happy ending vs. non-happy endings</div> 678 that arbitrary feature reduction steps such as stemming and stopword
679 removal should be taken very carefully, as they may affect the
680 prediction.
681 </p>
682 <p id="pid39"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid39">39</a>]</span>Volkova<a id="fna57" class="fn" href="#fn57" title="Volkova et al. 2010.">[57]</a> did not
683 focus on the classification of emotions automatically, but tackles
684 the task of annotation in more detail. The authors observe that
685 annotation of literature, in their case fairy tales, is challenging,
686 and that it is hard to obtain an acceptable annotation agreement. An
687 interesting innovative element in this study is that annotators were
688 not presented a predefined unit to annotate – they were allowed to
689 decide by themselves which granularity is most reasonable. That is
690 different to the other studies mentioned before in this section.
691 Further, a main finding was that short instances lead to a lower
692 agreement.
693 </p>
694 <p id="pid40"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid40">40</a>]</span>Finally, an interesting study by Ashok et al.<a id="fna58" class="fn" href="#fn58" title="Ashok et al. 2013?.">[58]</a> did not classify
695 emotions regarding a variable motivated by literary studies. They
696 use sentiment polarity as one component to predict the success of a
697 book. While such studies (similarly the prediction of citation
698 counts, etc.) are often criticized, the authors present some
699 interesting, but also perhaps non-surprising findings, e.g. that
700 unsuccessful stories contain more discriminative words that have a
701 negative connotation.
702 </p>
703 </div><a name="div15"> </a><div id="subchapter"><a name="hd13"> </a><h3>
704 <div style="position:relative;width:90%;">4.1.2 Classification of happy ending vs. non-happy
705 endings
706 </div>
492 </h3> 707 </h3>
493 <p>Zehe et al.<a id="fna52" class="fn" href="#fn52" title="Zehe et&nbsp;al. 2016, passim.">[52]</a> argue that automatically 708 <p id="pid41"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid41">41</a>]</span>A particular use case of emotion classification is to look closer
494 recognizing a happy ending as a major plot element could help to better understand 709 at particular parts of a text. Zehe et al.<a id="fna59" class="fn" href="#fn59" title="Zehe et&nbsp;al. 2016.">[59]</a> argue that automatically
495 a 710 recognizing a happy ending as a major plot element could help to
496 plot structure as a whole. To show that this is possible, they classify 212 German 711 better understand a plot structure as a whole. To show that this
497 novels written between 1750 and 1920 as having happy or non-happy endings. A novel 712 is possible, they classify 212 German novels written between
498 is 713 1750 and 1920 as having happy or non-happy endings. A novel is
499 considered to have a happy ending if the situation of the main characters in the 714 considered to have a happy ending if the situation of the main
500 novel improves towards the end or is constantly favorable. The novels were manually 715 characters in the novel improves towards the end or is
501 annotated with this information by domain experts. For feature extraction, the 716 constantly favorable. The novels were manually annotated with
502 authors first split each novel into <i>n</i> segments of the same 717 this information by domain experts. For feature extraction, the
503 length. They then calculate sentiment values for each of the segments by counting 718 authors first split each novel into <i>n</i>
504 the 719 segments of the same length. They then calculate sentiment
505 occurrences of words that appear in the respective segment and that are found in the 720 values for each of the segments based on a normalized word
506 German version of the <i>NRC Word-Emotion Association Lexicon</i><a id="fna53" class="fn" href="#fn53" title="Mohammad / Turney 2013, passim.">[53]</a> and divide this number by the 721 frequency with a German version of the <i>NRC Word-Emotion Association
507 length of the dictionary. Finally, they calculate the sentiment score for the 722 Lexicon</i>.
508 sections by taking the average of all sentiment scores in the segments that are part 723 <a id="fna60" class="fn" href="#fn60" title="Mohammad / Turney 2013.">[60]</a> An
509 of the section. These steps are then followed by classification with a support-vector 724 automatic sentiment classification with support vector machines
510 machine and the F1 score of 0.73, which the authors consider a good starting point 725 achieves reasonable and encouraging results.
511 for future work. 726 </p>
512 </p> 727 </div>
513 </div> 728 </div><a name="div16"> </a><div id="subchapter"><a name="hd14"> </a><h3>
514 </div>
515 <div id="subchapter"><a name="hd12"> </a><h3>
516 <div style="position:relative;width:90%;">4.2 Genre and Story-type Classification</div> 729 <div style="position:relative;width:90%;">4.2 Genre and Story-type Classification</div>
517 </h3> 730 </h3>
518 <p>The papers we have discussed so far focus on understanding the emotion associated 731 <p id="pid42"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid42">42</a>]</span>The papers we have discussed so far focus on understanding
519 with units of texts. This extracted information can further be used for downstream 732 the emotion associated with units of texts. This extracted
520 tasks and also for downstream evaluations. We discuss the following downstream 733 information can further be used for downstream tasks and
521 classification cases here. The papers in this category use sentiment and emotion 734 also for downstream evaluations. In the following, we
522 features for a higher-level classification, namely story-type clustering and literary 735 discuss downstream classification cases. The papers in this
523 genre classification. The assumption behind these works is that different types of 736 category use sentiment and emotion features for a
524 literary text may show different composition and distribution of emotion vocabulary 737 higher-level classification, namely story-type clustering
525 and thus can be classified based on this information. The hypothesis that different 738 and literary genre classification. The assumption behind
526 literary genres convey different emotions stems from common knowledge: we know that 739 these works is that different types of literary text may
527 horror stories instill <i>fear</i> and that mysteries evoke <i>anticipation</i> and <i>anger</i> while romances 740 show different composition and distribution of emotion
528 are filled with <i>joy</i> and <i>love</i>. However 741 vocabulary and thus can be classified based on this
529 as we will see in this section, the task of automatic classification of these genres 742 information. The hypothesis that different literary genres
530 is not always that straightforward and reliable. 743 convey different emotions stems from common knowledge: we
531 </p> 744 know that horror stories instill <i>fear</i>
532 <div id="subchapter"><a name="hd13"> </a><h3> 745 and that mysteries evoke <i>anticipation</i>
746 and <i>anger</i> while romances are filled
747 with <i>joy</i> and <i>love</i>. However as we will see in this section, the
748 task of automatic classification of these genres is not
749 always that straightforward and reliable.
750 </p><a name="div17"> </a><div id="subchapter"><a name="hd15"> </a><h3>
533 <div style="position:relative;width:90%;">4.2.1 Story-type clustering</div> 751 <div style="position:relative;width:90%;">4.2.1 Story-type clustering</div>
534 </h3> 752 </h3>
535 <p>Similarly to Zehe et al., Reagan et al.<a id="fna54" class="fn" href="#fn54" title="Reagan et&nbsp;al. 2016, passim.">[54]</a> are interested in automatically understanding a plot structure as a 753 <p id="pid43"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid43">43</a>]</span>Similarly to Zehe et al., Reagan et al.<a id="fna61" class="fn" href="#fn61" title="Reagan et&nbsp;al. 2016.">[61]</a> are
536 whole, not limited to a book ending. The inspiration for their work comes from Kurt 754 interested in automatically understanding a plot
537 Vonnegut’s lecture on emotional arcs of stories.<a id="fna55" class="fn" href="#fn55" title="Vonnegut 2010 (2005), passim.">[55]</a> 755 structure as a whole, but not limited to a book ending.
538 Reagan et al. test the idea that the plot 756 The inspiration for their work comes from Kurt
539 of each story can be plotted as an <i>emotional arc</i>, i.e. a time 757 Vonnegut’s lecture on emotional arcs of stories.<a id="fna62" class="fn" href="#fn62" title="Vonnegut 2010 (2005).">[62]</a> Reagan
540 series graph, where the <i>x</i>-axis represents a time point in a 758 et al. test the idea that the plot of each story can be
541 story, and the <i>y</i>-axis represents the events happening to the 759 visualized as an <i>emotional arc</i>,
542 main characters that can be favorable (peaks on a graph) or unfavorable (troughs on 760 i.e., a time series graph, where the <i>x</i>-axis represents a time point in a story, and
543 a 761 the <i>y</i>-axis represents the events
544 graph). As Vonnegut puts it, the stories can be grouped by these <i>arcs</i> and the number of such groupings is limited. To test this idea, Reagan 762 happening to the main characters that can be favorable
545 et al. collect the 1,327 most popular books from the <a href="https://www.gutenberg.org/" target="_blank">Project Gutenberg</a>.<a id="fna56" class="fn" href="#fn56" title="Project Gutenberg 1971-2019.">[56]</a> Each book is then split into segments for which 763 (peaks on a graph) or unfavorable (troughs on a graph).
546 sentiment scores (<i>happy</i> vs. <i>sad</i>) are 764 As Vonnegut puts it, the stories can be grouped by these
547 calculated and compared. The results of the analysis show support for six emotional 765 <i>arcs</i> and the number of such
548 patterns that are shared between subgroupings of the corpus: 766 groupings is limited. To test this idea, Reagan et al.
549 </p> 767 collect the 1,327 most popular books from the <a href="https://www.gutenberg.org/" target="_blank">Project
550 <ul class="ul_article"> 768 Gutenberg</a>.<a id="fna63" class="fn" href="#fn63" title="Project Gutenberg 1971–2019 [Webseite aus Deutschland nicht mehr erreichbar].">[63]</a> Each book is then split into
551 <li>Rise: the arc starts at a low point and steadily increases towards the end; </li> 769 segments for which happiness scores are calculated and
552 <li>Fall: the arc starts at a high point and steadily decreases towards the end; </li> 770 compared. The results of the analysis show support for
553 <li>Fall-rise: the arc drops in the middle of the story but increases towards the 771 six emotional patterns that are shared between
554 end; 772 subgroupings of the corpus. Additionally, Reagan et al.
555 </li> 773 find that some patterns are more popular among readers,
556 <li>Rise-fall: the arc hits the high point in the middle of the story and decreases 774 based on download counts, than others.
557 towards the end; 775 </p>
558 </li> 776 </div><a name="div18"> </a><div id="subchapter"><a name="hd16"> </a><h3>
559 <li>Rise-fall-rise: the arc fluctuates between high and low points but ends with an
560 increase;
561 </li>
562 <li>Fall-rise-fall: the arc fluctuates between high and low points but ends with a
563 decrease.
564 </li>
565 </ul>
566 <p>Additionally, Reagan et al. find that <i>Icarus</i>, <i>Oedipus</i>, and <i>Man in the hole</i> arcs are
567 the three most popular emotional arcs among readers, based on download counts.
568 </p>
569 </div>
570 <div id="subchapter"><a name="hd14"> </a><h3>
571 <div style="position:relative;width:90%;">4.2.2 Genre classification</div> 777 <div style="position:relative;width:90%;">4.2.2 Genre classification</div>
572 </h3> 778 </h3>
573 <p>There are other studies<a id="fna57" class="fn" href="#fn57" title="Samothrakis / Fasli 2015; Kim et&nbsp;al. 2017a; Kim et&nbsp;al. 2017b.">[57]</a> that are similar in spirit to the work done by 779 <p id="pid44"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid44">44</a>]</span>There are other studies<a id="fna64" class="fn" href="#fn64" title="Samothrakis / Fasli 2015; Kim et&nbsp;al. 2017a; Kim et&nbsp;al. 2017b.">[64]</a> that are similar in spirit to
574 Reagan. Samothrakis and Fasli examine the hypothesis that different genres clearly 780 the work done by Reagan et al. Samothrakis and Fasli
575 have different emotion patterns to reliably classify them with machine learning. To 781 examine the hypothesis that different genres clearly
576 that end, they collect works of the genres <i>mystery</i>, <i>humor</i>, <i>fantasy</i>, <i>horror</i>, <i>science fiction</i> and <i>western</i> from the Project Gutenberg. 782 have different emotion patterns to reliably classify
577 </p> 783 them with machine learning. To that end, they
578 <p>Using WordNet-Affect<a id="fna58" class="fn" href="#fn58" title="Strapparava / Valitutti 2004.">[58]</a> to 784 collect works of the genres <i>mystery</i>, <i>humor</i>, <i>fantasy</i>, <i>horror</i>, <i>science
579 detect emotion words as categorized by Ekman’s fundamental emotion classes, they 785 fiction</i> and <i>western</i>
580 calculate an emotion score for each sentence in the text. Each work is then 786 from the Project
581 transformed into six vectors, one for each basic emotion. A random forest classifier 787 Gutenberg. Using <a href="https://wndomains.fbk.eu/wnaffect.html" target="_blank">WordNet-Affect</a><a id="fna65" class="fn" href="#fn65" title="Strapparava / Valitutti 2004.">[65]</a> to detect emotion words as
582 achieves a classification accuracy of 0.52. This is significantly higher than a 788 categorized by Ekman’s fundamental emotion classes,
583 random baseline, which allows the authors to conclude that such a classification is 789 they calculate an emotion score for each sentence in
584 feasible. 790 the text. Each work is then transformed into six
585 </p> 791 vectors, one for each basic emotion. With a random
586 <p>A study by Kim et al.<a id="fna59" class="fn" href="#fn59" title="Kim et&nbsp;al. 2017a, passim.">[59]</a> originates from 792 forrest classifier, they show that genre
587 the same premise as the work by Samothrakis and Fasli but puts emphasis on finding 793 classification is possible based on this information
588 genre-specific correlations of emotion developments. Extending the set of tracked 794 with performance scores significantly above
589 emotions to Plutchik’s classification, Kim et al. collect 2,000 books from the 795 average.
590 Project Gutenberg that belong to five genres found in the Brown corpus<a id="fna60" class="fn" href="#fn60" title="Francis / Kucera 1979, passim.">[60]</a>, namely <i>adventure</i>, <i>science fiction</i>, <i>mystery</i>, <i>humor</i> and <i>romance</i>. 796 </p>
591 The authors extend the set of classification algorithms beyond random forests using 797 <p id="pid45"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid45">45</a>]</span>The study by Kim et al.<a id="fna66" class="fn" href="#fn66" title="Kim et&nbsp;al. 2017a.">[66]</a> originates from the same
592 a 798 premise as the work by Samothrakis and Fasli but
593 <span style="color:#035151"><i>multi-layer perceptron</i></span> and <span style="color:#035151"><i>convolutional 799 puts emphasis on finding genre-specific correlations
594 neural networks</i></span>, which achieves the best performance (0.59 F1-score). To 800 of emotion developments. They therefore link the
595 understand how uniform the emotion patterns in different genres are, the authors 801 motivation of Reagan et al. with the one by
596 introduce the notion of <i>prototypicality</i>, which is computed as 802 Samothrakis and Fasli. Extending the set of tracked
597 average of all emotion scores. Using this as a point of reference for each genre Kim 803 emotions to Plutchik’s classification, Kim et al.
598 et al. use Spearman correlation to calculate the uniformity of emotions per genre. 804 collect 2,000 books from the Project Gutenberg that
599 The results of this analysis suggest that <i>fear</i> and <i>anger</i> are the most salient plot devices in fiction, while <i>joy</i> is only of mediocre stability, which is in line with 805 belong to five genres found in the Brown corpus,<a id="fna67" class="fn" href="#fn67" title="Francis / Kucera 1979.">[67]</a>
600 findings of Samothrakis and Fasli. 806 namely <i>adventure</i>, <i>science fiction</i>, <i>mystery</i>, <i>humor</i> and <i>romance</i>.
601 </p> 807 The authors extend the set of classification
602 <p>The study by Henny-Krahmer<a id="fna61" class="fn" href="#fn61" title="Henny-Krahmer 2018, passim.">[61]</a> pursues 808 algorithms beyond random forests using a <span style="color:#035151"><i>multi-layer perceptron</i></span> and <span style="color:#035151"><i>convolutional neural networks</i></span>,
603 two goals: 1), to test whether different subgenres of Spanish American literature 809 which achieves the best performance. To understand
604 differ in degree and kind of emotionality, and 2), whether emotions in the novels 810 how uniform the emotion patterns in different genres
605 are 811 are, the authors introduce the notion of <i>prototypicality</i>, which is
606 expressed in direct speech of characters or in narrated text. To that end, they 812 computed as average of all emotion scores. Using
607 conduct a subgenre classification experiment on a corpus of Spanish American novels 813 this as a point of reference for each genre Kim et
608 using sentiment values as features. To answer the first question, each novel is split 814 al. use Spearman correlation to calculate the
609 into five segments and for each sentence in the segment the emotion score (polarity 815 uniformity of emotions per genre. The results of
610 values + Plutchik’s basic emotions) is calculated using SentiWordNet<a id="fna62" class="fn" href="#fn62" title="Baccianella et&nbsp;al. 2010.">[62]</a> and NRC<a id="fna63" class="fn" href="#fn63" title="Mohammad / Turney 2013.">[63]</a> dictionaries. The classifier achieves an average F1 816 this analysis suggest that <i>fear</i> and <i>anger</i> are
611 of 0.52, which is higher than the most-frequent class baseline and, hence, provides 817 the most salient plot devices in fiction, while <i>joy</i> is only of mediocre
612 a 818 stability, which is in line with findings of
613 support for emotion-based features in subgenre classification. The analysis of 819 Samothrakis and Fasli.
614 feature importance shows that the most salient features come from the sentiment 820 </p>
615 scores calculated from the characters’ direct speech and that novels with higher 821 <p id="pid46"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid46">46</a>]</span>The study by Henny-Khramer<a id="fna68" class="fn" href="#fn68" title="Henny-Krahmer 2018.">[68]</a> pursues two goals: 1),
616 values of positive speech are more likely to be sentimental novels. 822 to test whether different subgenres of Spanish
617 </p> 823 American literature differ in degree and kind of
618 <p>There are some limitations to the studies presented in this section. On the one hand, 824 emotionality, and 2), whether emotions in the novels
619 it is questionable how reliable <span style="color:#035151"><i>coarse emotion scoring</i></span> is that 825 are expressed in direct speech of characters or in
620 takes into account only presence or absence of words found in specialized 826 narrated text. To that end, they conduct a subgenre
621 dictionaries and overlooks negations and modifiers that can either negate an emotion 827 classification experiment on a corpus of Spanish
622 word or increase/decrease its intensity. On the other hand, a limited view of the 828 American novels using sentiment values as features.
623 emotional content as a sum of emotion bearing words reserves no room for qualitative 829 To answer the first question, each novel is split
624 interpretation of the texts – it is not clear how one can distinguish between emotion 830 into five segments and for each sentence in the
625 words used by the author to express their sentiment, between words used to describe 831 segment the emotion score (polarity values +
626 characters’ feelings, and emotion words that characters use to address or describe 832 Plutchik’s basic emotions) is calculated using <a href="https://github.com/aesuli/SentiWordNet" target="_blank">SentiWordNet</a><a id="fna69" class="fn" href="#fn69" title="Baccianella et&nbsp;al. 2010.">[69]</a> and <a href="https://saifmohammad.com/WebPages/NRC-Emotion-Lexicon.htm" target="_blank">NRC</a><a id="fna70" class="fn" href="#fn70" title="Mohammad / Turney 2013.">[70]</a> dictionaries. The analysis of feature
627 other characters in a story. 833 importance shows that the most salient features come
628 </p> 834 from the sentiment scores calculated from the
629 </div> 835 characters’ direct speech and that novels with
630 </div> 836 higher values of positive speech are more likely to
631 <div id="subchapter"><a name="hd15"> </a><h3> 837 be sentimental novels. This is an interesting
632 <div style="position:relative;width:90%;">4.3 Temporal Change of Sentiment</div> 838 variant of the beforehand mentioned studies – it is
839 important to distinguish characters' speech from
840 other parts of the text.
841 </p>
842 <p id="pid47"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid47">47</a>]</span>There are some limitations to the studies presented
843 in this section. On the one hand, it is questionable
844 how reliable <span style="color:#035151"><i>coarse emotion
845 scoring</i></span> is that takes into account only
846 presence or absence of words found in specialized
847 dictionaries and overlooks negations and modifiers
848 that can either negate an emotion word or
849 increase/decrease its intensity. On the other hand,
850 a limited view of the emotional content as a sum of
851 emotion bearing words reserves no room for
852 qualitative interpretation of the texts – it is not
853 clear how one can distinguish between emotion words
854 used by the author to express their sentiment,
855 between words used to describe characters’ feelings,
856 and emotion words that characters use to address or
857 describe other characters in a story.
858 </p>
859 </div>
860 </div><a name="div19"> </a><div id="subchapter"><a name="hd17"> </a><h3>
861 <div style="position:relative;width:90%;">4.3 Structural Changes of Sentiment</div>
633 </h3> 862 </h3>
634 <p>The papers that we have reviewed so far approach the problem of sentiment and emotion 863 <p id="pid48"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid48">48</a>]</span>The papers that we have reviewed so far approach
635 analysis as a classification task. However, applications of sentiment analysis are 864 the problem of sentiment and emotion analysis as a
636 not only limited to classification. In other fields, for example computational social 865 classification task. However, applications of
637 sciences, sentiment analysis can be used for analyzing political preferences of the 866 sentiment analysis are not only limited to
638 electorate or for mining opinions about different products or topics. Similarly, 867 classification. In other fields, for example
639 several digital humanities studies incorporate sentiment analysis methods in a task 868 computational social sciences, sentiment analysis
640 of mining sentiments and emotions of people who lived in the past. The goal of these 869 can be used for analyzing political preferences of
641 studies is not only to recognize sentiments, but also to understand how they were 870 the electorate or for mining opinions about
871 different products or topics. Similarly, several
872 digital humanities studies incorporate sentiment
873 analysis methods in a task of mining sentiments
874 and emotions of people who lived in the past. The
875 goal of these studies is not only to recognize
876 sentiments, but also to understand how they were
642 formed. 877 formed.
643 </p> 878 </p><a name="div20"> </a><div id="subchapter"><a name="hd18"> </a><h3>
644 <div id="subchapter"><a name="hd16"> </a><h3>
645 <div style="position:relative;width:90%;">4.3.1 Topography of emotions</div> 879 <div style="position:relative;width:90%;">4.3.1 Topography of emotions</div>
646 </h3> 880 </h3>
647 <p>Heuser et al.<a id="fna64" class="fn" href="#fn64" title="Heuser et&nbsp;al. 2016, passim.">[64]</a> start with a premise 881 <p id="pid49"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid49">49</a>]</span>Heuser et al.<a id="fna71" class="fn" href="#fn71" title="Heuser et&nbsp;al. 2016.">[71]</a> start with a premise that
648 that emotions occur at a specific moment in time and space, thus making it possible 882 emotions occur at a specific moment in time and
649 to link emotions to specific geographical locations. Consequently, having such 883 space, thus making it possible to link emotions to
650 information at hand, one can understand which emotions are hidden behind certain 884 specific geographical locations. Consequently,
651 landmarks. As a <span style="color:#035151"><i>proof-of-concept</i></span>, Heuser et al. build an interactive map, <a href="https://www.historypin.org/en/victorian-london/" target="_blank"> 885 having such information at hand, one can
652 Mapping emotions in Victorian London</a><a id="fna65" class="fn" href="#fn65" title="Historypin 2010-2017.">[65]</a>, where each location is tagged with emotion 886 understand which emotions are hidden behind
653 labels. To construct a corpus for their analysis, Heuser et al. collect a large 887 certain landmarks. As a <span style="color:#035151"><i>proof-of-concept</i></span>, Heuser et al. build an
654 corpus of English books from the eighteenth and nineteenth century and extract 383 888 <a href="https://www.historypin.org/en/victorian-london/" target="_blank"> interactive map of emotions</a>
655 geographical locations of London that have at least ten mentions each. The resulting 889 in Victorian London<a id="fna72" class="fn" href="#fn72" title="Historypin 2010–2017.">[72]</a>
656 corpus includes 15,000 passages, each of which has a toponym in the middle and 100 890 where each location is tagged with emotion labels.
657 words directly preceding and following the location mention. The data is then given 891 The underlying corpus for their analysis consists
658 to annotators who are asked to define whether each of the passages expressed <i>happiness</i> or <i>fear</i>, or <i>neutrality</i>. The same data is also analyzed by a custom sentiment analysis 892 of English books from the eighteenth and
659 program that would assign each passage one of these emotion categories. 893 nineteenth century, from which they extract
660 </p> 894 frequently mentioned geographical locations of
661 <p>Some striking observations are made with regard to the data analysis. First, there 895 London. The presegmented data is then given to
662 is 896 annotators who are asked to define whether each of
663 a clear discrepancy between fiction and reality – while toponyms from the West End 897 the passages expressed <i>happiness</i> or <i>fear</i>, or
664 with Westminster and the City are over-represented in the books, the same does not 898 <i>neutrality</i>. The same data
665 hold true for the East End with Tower Hamlets, Southwark, and Hackney. Hence, there 899 is further analyzed with a dictionary-based
666 is less information about emotions pertaining to these particular London locations. 900 sentiment classifier.
667 Another striking detail is that the resulting map is dominated by the neutral 901 </p>
668 emotion. Heuser et al. argue that this has nothing to do with the absence of emotions 902 <p id="pid50"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid50">50</a>]</span>Some striking observations are made with regard
669 but rather stems from the fact that emotions tend to be silenced in public domain, 903 to the data analysis. First, there is a clear
904 discrepancy between fiction and reality – while
905 toponyms from the West End with Westminster and
906 the City are over-represented in the books, the
907 same does not hold true for the East End with
908 Tower Hamlets, Southwark, and Hackney. Hence,
909 there is less information about emotions
910 pertaining to these particular London locations.
911 Another striking detail is that the resulting map
912 is dominated by the neutral emotion. Heuser et al.
913 argue that this has nothing to do with the absence
914 of emotions but rather stems from the fact that
915 emotions tend to be silenced in public domain,
670 which influenced the annotators decision. 916 which influenced the annotators decision.
671 </p> 917 </p>
672 <p>The space and time context are also used by Bruggman and Fabrikant<a id="fna66" class="fn" href="#fn66" title="Bruggmann / Fabrikant 2014, passim.">[66]</a> who model sentiments of Swiss 918 <p id="pid51"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid51">51</a>]</span>The space and time context are also used by
673 historians towards places in Switzerland in different historical periods. As the 919 Bruggman and Fabrikant<a id="fna73" class="fn" href="#fn73" title="Bruggmann / Fabrikant 2014.">[73]</a> who model
674 authors note, it is unlikely that a historian will directly express attitudes towards 920 sentiments of Swiss historians towards places in
675 certain toponyms, but it is very likely that words they use to describe those can 921 Switzerland in different historical periods. As
676 bear some negative connotation (e.g. cholera, death). Correspondingly, such places 922 the authors note, it is unlikely that a historian
677 should be identified as bearing negative sentiment by a sentiment analysis tool. 923 will directly express attitudes towards certain
678 Additionally, they study the changes of sentiment towards a particular place over 924 toponyms, but it is very likely that words they
679 time. Using the <i>General Inquirer</i> (GI) lexicon<a id="fna67" class="fn" href="#fn67" title="Stone et&nbsp;al. 1968.">[67]</a> to identify 925 use to describe those can bear some negative
680 positive and negative terms in the document, they assign each document a sentiment 926 connotation (e.g. cholera, death).
681 score by summing up the weights of negative and positive words and normalizing them 927 Correspondingly, such places should be identified
682 by the document length. The authors conclude that the results of their analysis look 928 as bearing negative sentiment by a sentiment
683 promising, especially regarding negatively scored articles. However, the authors find 929 analysis tool. Additionally, they study the
684 difficulties in interpreting positively ranked documents, which may be due to the 930 changes of sentiment towards a particular place
685 fact that negative information is more salient. 931 over time. Using the <i>General Inquirer</i> (GI) lexicon<a id="fna74" class="fn" href="#fn74" title="Stone et&nbsp;al. 1968.">[74]</a> to identify positive and
686 </p> 932 negative terms in the document, they assign
687 </div> 933 sentiment scores and conclude that the results of
688 <div id="subchapter"><a name="hd17"> </a><h3> 934 their analysis look promising, especially
935 regarding negatively scored articles.
936 </p>
937 </div><a name="div21"> </a><div id="subchapter"><a name="hd19"> </a><h3>
689 <div style="position:relative;width:90%;">4.3.2 Tracking sentiment</div> 938 <div style="position:relative;width:90%;">4.3.2 Tracking sentiment</div>
690 </h3> 939 </h3>
691 <p>Other papers in this category link sentiment and emotion to certain groups, rather 940 <p id="pid52"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid52">52</a>]</span>Other papers in this category link sentiment
692 than geographical locations. The goal of these studies is to understand how sentiment 941 and emotion to certain groups, rather than
693 within and towards these groups was formed. 942 geographical locations. The goal of these studies
694 </p> 943 is to understand how sentiment within and towards
695 <p>Taboada et al.<a id="fna68" class="fn" href="#fn68" title="Taboada et&nbsp;al. 2006, passim; Taboada et&nbsp;al. 2008, passim.">[68]</a> 944 these groups was formed.
696 aim at tracking the literary reputation of six authors writing in the first half of 945 </p>
697 the twentieth century. The research questions raised in the project are how the 946 <p id="pid53"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid53">53</a>]</span>Taboada et al.<a id="fna75" class="fn" href="#fn75" title="Taboada et&nbsp;al. 2006; Taboada et&nbsp;al. 2008.">[75]</a> aim at
698 reputation is made or lost, and how to find correlation between what is written about 947 tracking the literary reputation of six authors
699 the author and their work to the author’s reputation and subsequent canonicity. To 948 writing in the first half of the twentieth
700 that end, the project’s goal is to examine critical reviews of six authors’ writing 949 century. The research questions raised in the
701 and to map information contained in texts critical to the author’s reputation. The 950 project are how the reputation is made or lost,
702 material they work with includes not only reviews, but also press notes, press 951 and how to find correlation between what is
703 articles, and letters to editors (including from the authors themselves). For the 952 written about the authors and their work to the
704 pilot project with Galsworthy and Lawrence they collected and scanned 330 documents 953 authors’ reputation and subsequent canonicity. The
705 (480,000 words). The documents are tagged for the parts of speech and relevant words 954 project’s goal is to examine critical reviews of
706 (positive and negative) are extracted using custom-made sentiment dictionaries. The 955 six authors’ writing and to map information
707 sentiment orientation of rhetorically important parts of the texts is then measured. 956 contained in texts critical to the author’s
708 957 reputation. The material they work with includes
709 </p> 958 not only reviews, but also press notes, press
710 <p>Chen et al.<a id="fna69" class="fn" href="#fn69" title="Chen et&nbsp;al. 2012, passim.">[69]</a> aim to understand personal 959 articles, and letters to editors (including from
711 narratives of Korean <i>comfort women</i> who had been forced into 960 the authors themselves). They collected and
712 sexual slavery by Japanese military during World War II. Adapting the <i>WordNet-Affect</i> lexicon,<a id="fna70" class="fn" href="#fn70" title="Strapparava / Valitutti 2004.">[70]</a> Chen et 961 scanned 330 documents and tagged them with
713 al. build their own emotion dictionary to spot emotional keywords in women’s stories 962 polarity words with custom-made sentiment
714 and map the sentences to emotion categories. By adding variables of time and space, 963 dictionaries. The sentiment orientation of
715 Chen et al. provide a unified framework of collective remembering of this historical 964 rhetorically important parts of the texts is then
716 event as witnessed by the victims. 965 measured. The authors conclude that the current
717 </p> 966 approach has mostly been limited by a
718 <p>Finally, an interesting project to follow is the <a href="https://oceanicexchanges.org/" target="_blank">Oceanic Exchanges</a><a id="fna71" class="fn" href="#fn71" title="Oceanic Exchanges 2017.">[71]</a> project that started in late 2017. One goal of the project is 967 non-sufficiently large lexicon.
719 to trace information exchange in nineteenth-century newspapers and journals using 968 </p>
720 sentiment as one of the variables under analysis. 969 <p id="pid54"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid54">54</a>]</span>Chen et al.<a id="fna76" class="fn" href="#fn76" title="Chen et&nbsp;al. 2012.">[76]</a> aim to understand personal narratives
721 </p> 970 of Korean <i>comfort women</i> who
722 </div> 971 had been forced into sexual slavery by Japanese
723 <div id="subchapter"><a name="hd18"> </a><h3> 972 military during World War II. Adapting the <i>WordNet-Affect</i> lexicon,<a id="fna77" class="fn" href="#fn77" title="Strapparava / Valitutti 2004.">[77]</a> Chen et al. build their
724 <div style="position:relative;width:90%;">4.3.3 Sentiment recognition in historical texts</div> 973 own emotion dictionary to spot keywords in women’s
974 stories and map the sentences to emotion
975 categories. By adding variables of time and space,
976 Chen et al. provide a unified framework of
977 collective remembering of this historical event as
978 witnessed by the victims.
979 </p>
980 <p id="pid55"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid55">55</a>]</span>An interesting methodological contribution has
981 been made by Gao et al.<a id="fna78" class="fn" href="#fn78" title="Geo et al. 2016.">[78]</a> Instead of using raw counts of
982 polarity words over time, they propose that
983 filters are used to smooth the time series, which
984 further allows for other downstream
985 applications.
986 </p>
987 </div><a name="div22"> </a><div id="subchapter"><a name="hd20"> </a><h3>
988 <div style="position:relative;width:90%;">4.3.3 Sentiment recognition in historical
989 texts
990 </div>
725 </h3> 991 </h3>
726 <p>Other papers put emphasis not so much on the sentiments expressed by writers but 992 <p id="pid56"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid56">56</a>]</span>Other papers put emphasis not so much on the
727 instead focus on the particularities of historical language. 993 sentiments expressed by writers but instead focus
728 </p> 994 on the particularities of historical language.
729 <p>Marchetti et al.<a id="fna72" class="fn" href="#fn72" title="Marchetti et&nbsp;al. 2014, passim.">[72]</a> and Sprugnoli et 995 Marchetti et al.<a id="fna79" class="fn" href="#fn79" title="Marchetti et&nbsp;al. 2014.">[79]</a> and Sprugnoli et al.<a id="fna80" class="fn" href="#fn80" title="Sprugnoli et&nbsp;al. 2016.">[80]</a>
730 al. 996 present the integration of sentiment analysis in
731 <a id="fna73" class="fn" href="#fn73" title="Sprugnoli et&nbsp;al. 2016, passim.">[73]</a> present the integration of 997 the <a href="https://alcidedigitale.fbk.eu/" target="_blank">ALCIDE</a> (Analysis of Language and Content in
732 sentiment analysis in the <a href="http://celct.fbk.eu:8080/Alcide_Demo/" target="_blank">ALCIDE</a> (Analysis of Language and Content In a Digital Environment) 998 a Digital Environment) project.<a id="fna81" class="fn" href="#fn81" title="ALCIDE Demo 2014–2015.">[81]</a> The sentiment
733 project<a id="fna74" class="fn" href="#fn74" title="ALCIDE Demo 2014-2015.">[74]</a>. The sentiment analysis module is 999 analysis module is based on <span style="color:#035151"><i>WordNet-Affect</i></span>, <span style="color:#035151"><i>SentiWordNet</i></span><a id="fna82" class="fn" href="#fn82" title="Baccianella et&nbsp;al. 2010.">[82]</a> and <span style="color:#035151"><i>MultiWordNet</i></span>.<a id="fna83" class="fn" href="#fn83" title="Pianta et&nbsp;al. 2002.">[83]</a> Each document is assigned a
734 based on <span style="color:#035151"><i>WordNet-Affect</i></span>, <span style="color:#035151"><i>SentiWordNet</i></span><a id="fna75" class="fn" href="#fn75" title="Baccianella et&nbsp;al. 2010, passim.">[75]</a> and <span style="color:#035151"><i>MultiWordNet</i></span>.<a id="fna76" class="fn" href="#fn76" title="Pianta et&nbsp;al. 2002, passim.">[76]</a> Each 1000 normalized polarity score. The overall conclusion
735 document is assigned a polarity score by summing up the words with prior polarity 1001 of their work is that the assignment of a polarity
736 and 1002 in the historical domain is a challenging task
737 dividing by the number of words in the document. A positive global score leads to 1003 largely due to lack of agreement on polarity of
738 a 1004 historical sources between human annotators.
739 positive document polarity and a negative global score leads to a negative document 1005 </p>
740 polarity. The overall conclusion of their work is that the assignment of a polarity 1006 <p id="pid57"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid57">57</a>]</span>Challenged by the problem of applicability of
741 in the historical domain is a challenging task largely due to lack of agreement on 1007 existing emotion lexicons to historical texts,
742 polarity of historical sources between human annotators. 1008 Buechel et al.<a id="fna84" class="fn" href="#fn84" title="Buechel et&nbsp;al. 2017.">[84]</a> propose a new method of
743 </p> 1009 constructing affective lexicons that would adapt
744 <p>Challenged by the problem of applicability of existing emotion lexicons to historical 1010 well to German texts written up to three centuries
745 texts, Buechel et al.<a id="fna77" class="fn" href="#fn77" title="Buechel et&nbsp;al. 2017, passim.">[77]</a> propose a new 1011 ago. In their study, Buechel et al. use the
746 method of constructing affective lexicons that would adapt well to German texts 1012 representation of affect based on the <span style="color:#035151"><i>Valence-Arousal-Dominance model</i></span>
747 written up to three centuries ago. In their study, Buechel et al. use the 1013 (an adaptation of Russel’s circumplex model, see
748 representation of affect based on the <span style="color:#035151"><i>Valence-Arousal-Dominance 1014 <a title="" href="#hd8">section
749 model</i></span> (an adaptation of Russel’s circumplex model, see <a title="" href="#hd6">Section 2.3</a>). 1015 2.3</a>). Presumably, such a representation
750 Presumably, such a representation provides a finer-grained insight into the literary 1016 provides a finer-grained insight into the literary
751 text,<a id="fna78" class="fn" href="#fn78" title="Buechel et&nbsp;al. 2016, p. 54, p. 59.">[78]</a> which is more expressive 1017 text,<a id="fna85" class="fn" href="#fn85" title="Buechel et&nbsp;al. 2016 p. 54, p. 59.">[85]</a>, which is more expressive than
752 than discrete categories, as it quantifies the emotion along three different 1018 discrete categories, as it quantifies the emotion
753 dimensions. As a basis for the analysis, they collect German texts from the <a href="http://www.deutschestextarchiv.de/" target="_blank">Deutsches Textarchiv</a><a id="fna79" class="fn" href="#fn79" title="Deutsches Textarchiv 2007-2019.">[79]</a> written 1019 along three different dimensions. As a basis for
754 between 1690 and 1899. The corpus is split into seven slices, each spanning 30 years. 1020 the analysis, they collect German texts from the
755 For each slice they compute word similarities and obtain seven distinct emotion 1021 <a href="http://www.deutschestextarchiv.de/" target="_blank">Deutsches Textarchiv</a><a id="fna86" class="fn" href="#fn86" title="Deutsches Textarchiv 2007–2019.">[86]</a> written between 1690
756 lexicons, each corresponding to specific time period. This allows for, the authors 1022 and 1899. The corpus is split into seven slices,
757 argue, the tracing of the shift in emotion association of words over time. 1023 each spanning 30 years. For each slice they
758 </p> 1024 compute word similarities and obtain seven
759 <p>Finally, Leemans et al.<a id="fna80" class="fn" href="#fn80" title="Leemans et&nbsp;al. 2017, passim.">[80]</a> aim to 1025 distinct emotion lexicons, each corresponding to
760 trace historical changes in emotion expressions and to develop methods to trace these 1026 specific time period. This allows for, the authors
761 changes in a corpus of 29 Dutch language theatre plays written between 1600 and 1800. 1027 argue, the tracing of the shift in emotion
762 Expanding the Dutch version of <i>Linguistic Inquiry and Word Count</i> (LIWC) dictionary<a id="fna81" class="fn" href="#fn81" title="Pennebaker et&nbsp;al. 2007.">[81]</a> with 1028 association of words over time.
763 historical terms, the authors are able to increase the recall of emotion recognition 1029 </p>
764 with a dictionary. In addition, they develop a fine-grained vocabulary mapping body 1030 <p id="pid58"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid58">58</a>]</span>Finally, Leemans et al.<a id="fna87" class="fn" href="#fn87" title="Leemans et&nbsp;al. 2017.">[87]</a> aim to trace
765 terms to emotions, and show that a combination of LIWC and their lexicon lead to 1031 historical changes in emotion expressions and to
1032 develop methods to trace these changes in a corpus
1033 of 29 Dutch language theatre plays written between
1034 1600 and 1800. Expanding the Dutch version of <i>Linguistic Inquiry and Word
1035 Count</i> (LIWC) dictionary<a id="fna88" class="fn" href="#fn88" title="Pennebaker et&nbsp;al. 2007.">[88]</a> with historical
1036 terms, the authors are able to increase the recall
1037 of emotion recognition with a dictionary. In
1038 addition, they develop a fine-grained vocabulary
1039 mapping body terms to emotions, and show that a
1040 combination of LIWC and their lexicon lead to
766 improvement in the emotion recognition. 1041 improvement in the emotion recognition.
768 </div> 1043 </div>
769 </div> 1044 </div><a name="div23"> </a><div id="subchapter"><a name="hd21"> </a><h3>
770 <div id="subchapter"><a name="hd19"> </a><h3> 1045 <div style="position:relative;width:90%;">4.4 Character Network Analysis and
771 <div style="position:relative;width:90%;">4.4 Character Network Analysis and Relationship Extraction</div> 1046 Relationship Extraction
1047 </div>
772 </h3> 1048 </h3>
773 <p>The papers reviewed above address sentiment analysis of literary texts mainly on a 1049 <p id="pid59"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid59">59</a>]</span>The papers reviewed above address sentiment
774 document level. This abstraction is warranted if the goal is to get an insight into 1050 analysis of literary texts mainly on a document
775 the distribution of emotions in a corpus of books. However, emotions depicted in 1051 level. This abstraction is warranted if the goal
776 books do not exist in isolation but are associated with characters who are at the 1052 is to get an insight into the distribution of
777 core of any literary narrative.<a id="fna82" class="fn" href="#fn82" title="Ingermanson / Economy 2009, p. 107.">[82]</a> This leads us to ask what sentiment and emotion analysis can tell us 1053 emotions in a corpus of books. However, emotions
778 about the characters. How emotional are they? And what role do emotions play in their 1054 depicted in books do not exist in isolation but
779 interaction? 1055 are associated with characters who are at the core
780 </p> 1056 of any literary narrative.<a id="fna89" class="fn" href="#fn89" title="Ingermanson / Economy 2009, p. 107.">[89]</a> This
781 <p>Character relationships have been analyzed in computational linguistics from a graph 1057 leads us to ask what sentiment and emotion
782 theoretic perspective, particularly using social network analysis.<a id="fna83" class="fn" href="#fn83" title="Agarwal et&nbsp;al. 2013; Elson et&nbsp;al. 2011.">[83]</a> Fewer works, 1058 analysis can tell us about the characters. How
783 however, address the problem of modeling character relationships in terms of 1059 emotional are they? And what role do emotions play
784 sentiment. Below we provide an overview of several papers that propose the 1060 in their interaction?
785 methodology for extracting this information. 1061 </p>
786 </p> 1062 <p id="pid60"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid60">60</a>]</span>Character relationships have been analyzed in
787 <div id="subchapter"><a name="hd20"> </a><h3> 1063 computational linguistics from a graph theoretic
788 <div style="position:relative;width:90%;">4.4.1 Sentiment dynamics between characters</div> 1064 perspective, particularly using social network
1065 analysis.<a id="fna90" class="fn" href="#fn90" title="Agarwal et&nbsp;al. 2013; Elson et&nbsp;al. 2011.">[90]</a> Fewer works,
1066 however, address the problem of modeling character
1067 relationships in terms of sentiment. Below we
1068 provide an overview of several papers that propose
1069 the methodology for extracting this information.
1070 </p><a name="div24"> </a><div id="subchapter"><a name="hd22"> </a><h3>
1071 <div style="position:relative;width:90%;">4.4.1 Sentiment dynamics between
1072 characters
1073 </div>
789 </h3> 1074 </h3>
790 <p>Several studies present automatic methods for analyzing sentiment dynamics between 1075 <p id="pid61"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid61">61</a>]</span>Several studies present automatic methods for
791 plays’ characters. The goal of the study by Nalisnick and Baird<a id="fna84" class="fn" href="#fn84" title="Nalisnick / Baird 2013a, passim.">[84]</a> is to track the emotional trajectories of 1076 analyzing sentiment dynamics between plays’
792 interpersonal relationships. The structured format of a dialog allows them to 1077 characters. The goal of the study by Nalisnick and
793 identify who is speaking to whom, which makes it possible to mine 1078 Baird<a id="fna91" class="fn" href="#fn91" title="Nalisnick / Baird 2013a.">[91]</a> is to track the emotional
794 character-to-character sentiment by summing the valence values of words that appear 1079 trajectories of interpersonal relationships. The
795 in the continuous direct speech and are found in the lexicon<a id="fna85" class="fn" href="#fn85" title="Nielsen 2011, passim.">[85]</a> 1080 structured format of a dialog allows them to
796 of affective norms. The extension<a id="fna86" class="fn" href="#fn86" title="Nalisnick / Baird 2013b, passim.">[86]</a> of the previous research from the same authors 1081 identify who is speaking to whom, which makes it
797 introduces the concept of a sentiment network, a dynamic social network of 1082 possible to mine character-to-character sentiment
798 characters. Changing polarities between characters are modeled as edge weights in 1083 by summing the valence values of words that appear
799 the 1084 in the continuous direct speech and are found in
800 network. Motivated by the desire to explain such networks in terms of a general 1085 the lexicon<a id="fna92" class="fn" href="#fn92" title="Nielsen 2011.">[92]</a> of affective norms. The
801 sociological model, Nalisnick and Baird test whether Shakespeare’s plays obey the 1086 extension<a id="fna93" class="fn" href="#fn93" title="Nalisnick / Baird 2013b.">[93]</a> of the previous research from the
802 <span style="color:#035151"><i>Structural Balance Theory</i></span> by Marvel et al.<a id="fna87" class="fn" href="#fn87" title="Marvel et&nbsp;al. 2011.">[87]</a> that postulates that a friend of a 1087 same authors introduces the concept of a
803 friend is also your friend. Using the procedure proposed by Marvel et al. on their 1088 »sentiment network«, a dynamic social
804 Shakespearean sentiment networks, Nalisnick and Baird test whether they can predict 1089 network of characters. Changing polarities between
805 how a play’s characters will split into factions using only information about the 1090 characters are modeled as edge weights in the
806 state of the sentiment network after Act II. The results of their analysis are varied 1091 network. Motivated by the desire to explain such
807 and do not provide adequate support for the Structural Balance Theory as a benchmark 1092 networks in terms of a general sociological model,
808 for network analysis in Shakespeare’s plays. One reason for that, as the authors 1093 Nalisnick and Baird test whether Shakespeare’s
809 state, is inadequacy of their shallow sentiment analysis methods that cannot detect 1094 plays obey the <span style="color:#035151"><i>Structural Balance
810 such elements of speech as irony and deceit that play a pivotal role in many literary 1095 Theory</i></span> by Marvel et al.<a id="fna94" class="fn" href="#fn94" title="Marvel et&nbsp;al. 2011.">[94]</a> that
811 works. 1096 postulates that a friend of a friend is also your
812 </p> 1097 friend. Using the procedure proposed by Marvel et
813 </div> 1098 al. on their Shakespearean sentiment networks,
814 <div id="subchapter"><a name="hd21"> </a><h3> 1099 Nalisnick and Baird test whether they can predict
815 <div style="position:relative;width:90%;">4.4.2 Character analysis and character relationships</div> 1100 how a play’s characters will split into factions
1101 using only information about the state of the
1102 sentiment network after Act II. The results of
1103 their analysis are varied and do not provide
1104 adequate support for the Structural Balance Theory
1105 as a benchmark for network analysis in
1106 Shakespeare’s plays. One reason for that, as the
1107 authors state, is inadequacy of their shallow
1108 sentiment analysis methods that cannot detect such
1109 elements of speech as irony and deceit that play a
1110 pivotal role in many literary works.
1111 </p>
1112 </div><a name="div25"> </a><div id="subchapter"><a name="hd23"> </a><h3>
1113 <div style="position:relative;width:90%;">4.4.2 Character analysis and character
1114 relationships
1115 </div>
816 </h3> 1116 </h3>
817 <p>Elsner<a id="fna88" class="fn" href="#fn88" title="Elsner 2012, passim; Elsner 2015, passim.">[88]</a> aims at answering the 1117 <p id="pid62"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid62">62</a>]</span>Elsner<a id="fna95" class="fn" href="#fn95" title="Elsner 2012; Elsner 2015.">[95]</a> aims at answering the question
818 question of how to represent a plot structure for summarization and generation tools. 1118 of how to represent a plot structure for
819 To that end, Elsner presents a <i>kernel</i> for comparing novelistic 1119 summarization and generation tools. To that end,
820 plots at the level of character interactions and their relationships. Using sentiment 1120 Elsner presents a <i>kernel</i>
821 as one of the characteristics of a character, Elsner demonstrates that the kernel 1121 for comparing novelistic plots at the level of
822 approach leads to meaningful plot representation that can be used for a higher-level 1122 character interactions and their relationships.
1123 Using sentiment as one of the properties of a
1124 character, Elsner demonstrates that the kernel
1125 approach leads to meaningful plot representation
1126 that can be used for a higher-level
823 processing. 1127 processing.
824 </p> 1128 </p>
825 <p>Kim and Klinger<a id="fna89" class="fn" href="#fn89" title="Kim / Klinger 2018, passim.">[89]</a> aim at understanding 1129 <p id="pid63"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid63">63</a>]</span>Kim and Klinger<a id="fna96" class="fn" href="#fn96" title="Kim / Klinger 2018.">[96]</a> aim at understanding the
826 the causes of emotions experienced by literary characters. To that end, they 1130 causes of emotions experienced by literary
827 contribute the <a href="http://www.ims.uni-stuttgart.de/data/reman" target="_blank">REMAN 1131 characters. To that end, they contribute the <a href="http://www.ims.uni-stuttgart.de/data/reman" target="_blank">REMAN corpus</a><a id="fna97" class="fn" href="#fn97" title="REMAN – Relational Emotion Annotation for Fiction. Corpus 2018.">[97]</a> of literary texts with
828 corpus</a><a id="fna90" class="fn" href="#fn90" title="REMAN - Relational Emotion Annotation for Fiction. Corpus 2018.">[90]</a> of literary texts with annotations of emotions, 1132 annotations of emotions, experiencers, causes and
829 experiencers, causes and targets of the emotions. The goal of the project is to 1133 targets of the emotions. The goal of the project
830 enable the automatic extraction of emotions and causes of emotions experienced by 1134 is to enable the automatic extraction of emotions
831 the 1135 and causes of emotions experienced by the
832 characters. The authors suggest that the results of coarse-grained emotion 1136 characters. The authors suggest that the results
833 classification in literary text are not readily interpretable as they do not tell 1137 of coarse-grained emotion classification in
834 much about who the experiencer of the emotion is. Indeed, if a text mentions two 1138 literary text are not readily interpretable as
835 characters, one of whom is <i>angry</i> and another one who is <i>scared</i> because of that, text classification models will only 1139 they do not tell much about who the experiencer of
836 tell us that the text is about <i>anger</i> and <i>fear</i>. Hence, a finer-grained approach towards character relationship 1140 the emotion is. Indeed, if a text mentions two
837 extraction is warranted. Kim and Klinger conduct experiments on the annotated dataset 1141 characters, one of whom is <i>angry</i> and another one who is <i>scared</i> because of that, text
838 showing that the fine-grained approach to emotion prediction with long short-term 1142 classification models will only tell us that the
839 memory networks outperforms <span style="color:#035151"><i>bag-of-words models</i></span> (an increase 1143 text is about <i>anger</i> and <i>fear</i>. Hence, a finer-grained
840 in F1 by 12 pp). At the same time, the results of their experiments suggest that 1144 approach towards character relationship extraction
841 joint prediction of emotions and experiencers can be more beneficial than studying 1145 is warranted. Kim and Klinger conduct experiments
842 these categories separately. 1146 on the annotated dataset showing that the
843 </p> 1147 fine-grained approach to emotion prediction with
844 <p>Barth et al.<a id="fna91" class="fn" href="#fn91" title="Barth et&nbsp;al. 2018, passim.">[91]</a> develop the character 1148 long short-term memory networks outperforms <span style="color:#035151"><i>bag-of-words models</i></span>. At the same
845 relation analysis tool <span style="color:#035151"><i>rCAT</i></span> with the goal of visualization and 1149 time, the results of their experiments suggest
846 analysis of character networks in a literary text. The tool implements a distance 1150 that joint prediction of emotions and experiencers
847 parameter (based on token space) for finding pairs of interacting characters. In 1151 can be more beneficial than studying these
848 addition to the general context words that characterize each pair of characters, the 1152 categories separately.
849 tool provides an emotion filter to restrict character relationship analysis to 1153 </p>
850 emotions only. 1154 <p id="pid64"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid64">64</a>]</span>A tool presented by Jhavar and Mirza<a id="fna98" class="fn" href="#fn98" title="Jhavar / Mirza 2018.">[98]</a>
851 </p> 1155 provides a similar functionality: given an input
852 <p>A tool presented by Jhavar and Mirza<a id="fna92" class="fn" href="#fn92" title="Jhavar / Mirza 2018, passim.">[92]</a> provides a similar functionality: given an input of two character 1156 of two character names from the <i>Harry Potter</i> series, the <a href="https://gate.d5.mpi-inf.mpg.de/emofiel/" target="_blank">EMoFiel</a><a id="fna99" class="fn" href="#fn99" title="EMoFiel: Emotion Mapping of Fictional Relationship 2018.">[99]</a> tool
853 names from the <i>Harry Potter</i> series, the <a href="https://gate.d5.mpi-inf.mpg.de/emofiel/" target="_blank">EMoFiel</a><a id="fna93" class="fn" href="#fn93" title="EMoFiel: Emotion Mapping of Fictional Relationship 2018.">[93]</a> tool identifies the emotion flow between a 1157 identifies the emotion flow between a given
854 given directed pair of story characters. These emotions are identified using 1158 directed pair of story characters. These emotions
855 categorical<a id="fna94" class="fn" href="#fn94" title="Plutchik 1991, passim.">[94]</a> and continuous<a id="fna95" class="fn" href="#fn95" title="Russell 1980, passim.">[95]</a> emotion models. 1159 are identified using categorical<a id="fna100" class="fn" href="#fn100" title="Plutchik 1991.">[100]</a> and
856 </p> 1160 continuous<a id="fna101" class="fn" href="#fn101" title="Russell 1980.">[101]</a> emotion models.
857 <p>Egloff et al.<a id="fna96" class="fn" href="#fn96" title="Egloff et&nbsp;al. 2018, passim.">[96]</a> present an ongoing 1161 </p>
858 work on the <span style="color:#035151"><i>Ontology of Literary Characters</i></span> (OLC) that allows 1162 <p id="pid65"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid65">65</a>]</span>Egloff et al.<a id="fna102" class="fn" href="#fn102" title="Egloff et&nbsp;al. 2018.">[102]</a> present an ongoing work on the
859 us to capture and infer characters’ psychological traits from their linguistic 1163 <span style="color:#035151"><i>Ontology of Literary
860 descriptions. The OLC incorporates the <span style="color:#035151"><i>Ontology of Emotion</i></span><a id="fna97" class="fn" href="#fn97" title="Patti et&nbsp;al. 2015.">[97]</a> that is based on both Plutchik’s and 1164 Characters</i></span> (OLC) that allows us to capture
861 Hourglass’s<a id="fna98" class="fn" href="#fn98" title="Cambria et&nbsp;al. 2012, passim.">[98]</a> models of emotions. 1165 and infer characters’ psychological traits from
862 The ontology encodes 32 emotion concepts. Based on their natural language 1166 their linguistic descriptions. The OLC
863 description, characters are attributed to a psychological profile along the classes 1167 incorporates the <span style="color:#035151"><i>Ontology of
864 of Openness to <i>experience</i>, <i>Conscientiousness</i>, <i>Extraversion</i>, <i>Agreeableness</i>, and <i>Neuroticism</i>. The ontology links 1168 Emotion</i></span><a id="fna103" class="fn" href="#fn103" title="Patti et&nbsp;al. 2015.">[103]</a>
865 each of these profiles to one or more archetypal categories of <i>hero</i>, <i>anti-hero</i>, and <i>villain</i>. 1169 that is based on both Plutchik’s and
866 Egloff et al. argue that, by using the semantic connections of the OLC, it is 1170 Hourglass’s<a id="fna104" class="fn" href="#fn104" title="Cambria et&nbsp;al. 2012.">[104]</a> models of emotions. The ontology
867 possible to infer the characters’ psychological profiles and the role they play in 1171 encodes 32 emotion concepts. Based on their
1172 natural language description, characters are
1173 attributed to a psychological profile along the
1174 classes of <i>Openness</i> to <i>experience</i>, <i>Conscientiousness</i>, <i>Extraversion</i>, <i>Agreeableness</i>, and <i>Neuroticism</i>. The ontology links each of
1175 these profiles to one or more archetypal
1176 categories of <i>hero</i>, <i>anti-hero</i>, and <i>villain</i>. Egloff et al. argue
1177 that, by using the semantic connections of the
1178 OLC, it is possible to infer the characters’
1179 psychological profiles and the role they play in
868 the plot. 1180 the plot.
869 </p> 1181 </p>
870 <p>Kim and Klinger<a id="fna99" class="fn" href="#fn99" title="Kim / Klinger 2019b, passim.">[99]</a> propose a new task 1182 <p id="pid66"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid66">66</a>]</span>Kim and Klinger<a id="fna105" class="fn" href="#fn105" title="Kim / Klinger 2019b.">[105]</a> propose the task of emotion
871 of emotion relationship classification between fictional characters. They argue that 1183 relationship classification between fictional
872 joining character network analysis with sentiment and emotion analysis may contribute 1184 characters. They argue that joining character
873 to a computational understanding of narrative structures, as characters are at the 1185 network analysis with sentiment and emotion
874 center of any plot development. Building a corpus of 19 fan fiction short stories 1186 analysis may contribute to a computational
875 and 1187 understanding of narrative structures, as
876 annotating it with emotions, Kim and Klinger propose several models to classify 1188 characters are at the center of any plot
877 emotion relations of characters. They show that a deep learning architecture with 1189 development. Building a corpus of 19 fan fiction
878 character position indicators is the best for the task of predicting both directed 1190 short stories and annotating it with emotions, Kim
879 and undirected emotion relations in the associated social network graph. As an 1191 and Klinger propose several models to classify
880 extension to this study, Kim and Klinger<a id="fna100" class="fn" href="#fn100" title="Kim / Klinger 2019a, passim.">[100]</a> explore how emotions are expressed between characters in the same 1192 emotion relations of characters. They show that a
881 corpus via various non-verbal communication channels.<a id="fna101" class="fn" href="#fn101" title="Their analysis is based on Van Meel 1995 we mentioned in Section 3.">[101]</a> They find 1193 deep learning architecture with character position
882 that facial expressions are predominantly associated with <i>joy</i> 1194 indicators is the best for the task of predicting
883 while gestures and body postures are more likely to occur with <i>trust</i>. 1195 both directed and undirected emotion relations in
884 </p> 1196 the associated social network graph. As an
885 <p>Finally, a small body of work focuses on mathematical modeling of character 1197 extension to this study, Kim and Klinger<a id="fna106" class="fn" href="#fn106" title="Kim / Klinger 2019a.">[106]</a>
886 relationships. Rinaldi et al.<a id="fna102" class="fn" href="#fn102" title="Rinaldi et&nbsp;al. 2013, passim.">[102]</a> 1198 explore how emotions are expressed between
887 contribute a model that describes the love story between the Beauty and the Beast 1199 characters in the same corpus via various
888 through ordinary differential equations. Zhuravlev et al.<a id="fna103" class="fn" href="#fn103" title="Zhuravlev et&nbsp;al. 2014, passim.">[103]</a> introduce a distance function to model the 1200 non-verbal communication channels.<a id="fna107" class="fn" href="#fn107" title="Their analysis is based on Van Meel 1995 we mentioned in section 3.">[107]</a> They find
889 relationship between the protagonist and other characters in two masochistic short 1201 that facial expressions are predominantly
890 novels by Ivan Turgenev and Sacher-Masoch. Borrowing some instruments from the 1202 associated with <i>joy</i> while
891 literary criticism and using ordinary differential equations, Zhuravlev et al. are 1203 gestures and body postures are more likely to
892 able to reproduce the temporal and spatial dynamics of the love plot in the two 1204 occur with <i>trust</i>.
893 novellas more precisely than it had been done in previous research. Jafari et 1205 </p>
894 al.<a id="fna104" class="fn" href="#fn104" title="Jafari et&nbsp;al. 2016, passim.">[104]</a> present a dynamic model 1206 <p id="pid67"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid67">67</a>]</span>Finally, a small body of work focuses on
895 describing the development of character relationships based on differential 1207 mathematical modeling of character relationships.
896 equations. The proposed model is enriched with complex variables that can represent 1208 Rinaldi et al.<a id="fna108" class="fn" href="#fn108" title="Rinaldi et&nbsp;al. 2013.">[108]</a> contribute a model that
897 complex emotions such as coexisting <i>love</i> and <i>hate</i>. 1209 describes the love story between the <i>Beauty and the Beast</i> through ordinary differential equations.
898 </p> 1210 Zhuravlev et al.<a id="fna109" class="fn" href="#fn109" title="Zhuravlev et&nbsp;al. 2014.">[109]</a> introduce a distance function
899 </div> 1211 to model the relationship between the protagonist
900 </div> 1212 and other characters in two masochistic short
901 <div id="subchapter"><a name="hd22"> </a><h3> 1213 novels by Ivan Turgenev and Sacher-Masoch.
1214 Borrowing some instruments from the literary
1215 criticism and using ordinary differential
1216 equations, Zhuravlev et al. are able to reproduce
1217 the temporal and spatial dynamics of the love plot
1218 in the two novellas more precisely than it had
1219 been done in previous research. Jafari et al.<a id="fna110" class="fn" href="#fn110" title="Jafari et&nbsp;al. 2016.">[110]</a>
1220 present a dynamic model describing the development
1221 of character relationships based on differential
1222 equations. The proposed model is enriched with
1223 complex variables that can represent complex
1224 emotions such as coexisting <i>love</i> and <i>hate</i>.
1225 </p>
1226 </div>
1227 </div><a name="div26"> </a><div id="subchapter"><a name="hd24"> </a><h3>
902 <div style="position:relative;width:90%;">4.5 Other Types of Emotion Analysis</div> 1228 <div style="position:relative;width:90%;">4.5 Other Types of Emotion Analysis</div>
903 </h3> 1229 </h3>
904 <p>We have seen that sentiment analysis as applied to literature can be used for a 1230 <p id="pid68"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid68">68</a>]</span>We have seen that sentiment analysis as applied
905 number of downstream tasks, such as classification of texts based on the emotions 1231 to literature can be used for a number of
906 they convey, genre classification based on emotions, and sentiment analysis in the 1232 downstream tasks, such as classification of texts
907 historical domain. However, the application of sentiment analysis is not limited to 1233 based on the emotions they convey, genre
908 these tasks. In this concluding part of the survey, we review some papers that do 1234 classification based on emotions, and sentiment
909 not 1235 analysis in the historical domain. However, the
910 formulate their approach to sentiment analysis as a downstream task. Often, the goal 1236 application of sentiment analysis is not limited
911 of these works is to understand how sentiments and emotions are represented in 1237 to these tasks. In this concluding part of the
912 literary texts in general, and how sentiment or emotion content varies across 1238 survey, we review some papers that do not
913 specific documents or a collection of them with time, where time can be either 1239 formulate their approach to sentiment analysis as
914 relative to the text in question (from beginning to end) or to the historical changes 1240 a downstream task. Often, the goal of these works
915 in language (from past to present). Such information is valuable for gaining a deeper 1241 is to understand how sentiments and emotions are
916 insight into how sentiments and emotions change over time, allowing us to bring 1242 represented in literary texts in general, and how
917 forward new theories or shed more light onto existing literary or sociological 1243 sentiment or emotion content varies across
918 theories. 1244 specific documents or a collection of them with
919 </p> 1245 time, where time can be either relative to the
920 <div id="subchapter"><a name="hd23"> </a><h3> 1246 text in question (from beginning to end) or to the
921 <div style="position:relative;width:90%;">4.5.1 Emotion flow analysis and visualization</div> 1247 historical changes in language (from past to
1248 present). Such information is valuable for gaining
1249 a deeper insight into how sentiments and emotions
1250 change over time, allowing us to bring forward new
1251 theories or shed more light onto existing literary
1252 or sociological theories.
1253 </p><a name="div27"> </a><div id="subchapter"><a name="hd25"> </a><h3>
1254 <div style="position:relative;width:90%;">4.5.1 Emotion flow analysis and
1255 visualization
1256 </div>
922 </h3> 1257 </h3>
923 <p>A set of authors aimed to visualize the change of emotion content through texts or 1258 <p id="pid69"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid69">69</a>]</span>A set of authors aimed to visualize the change
924 across time. One of the earliest works in this direction is a paper by Anderson and 1259 of emotion content through texts or across time.
925 McMaster<a id="fna105" class="fn" href="#fn105" title="Anderson / McMaster 1986, passim.">[105]</a> that starts from 1260 One of the earliest works in this direction is a
926 the premise that reading enjoyment stems from the affective tones of a text. These 1261 paper by Anderson and McMaster<a id="fna111" class="fn" href="#fn111" title="Anderson / McMaster 1986.">[111]</a>
927 affective tones create a conflict that can rise to a climax through a series of 1262 that starts from the premise that reading
928 crises, which is necessary for a work of fiction to be attractive to the reader. 1263 enjoyment stems from the affective tones of a
929 Using a list of 1,000 of the most common English words annotated with valence, 1264 text. These affective tones create a conflict that
930 arousal, and dominance ratings,<a id="fna106" class="fn" href="#fn106" title="Heise 1965, passim.">[106]</a> they 1265 can rise to a climax through a series of crises,
931 calculate the conflict score by taking the mean of the ratings for each word in a 1266 which is necessary for a work of fiction to be
932 text passage. The more negative the score is, the higher the conflict is, and vice 1267 attractive to the reader. Using a list of 1,000 of
933 versa. Additionally, they plot conflict scores for each consecutive 100 words of a 1268 the most common English words annotated with
934 test story and provide qualitative analysis of the peaks. They argue that a reader 1269 valence, arousal, and dominance ratings,<a id="fna112" class="fn" href="#fn112" title="Heise 1965.">[112]</a> they calculate
935 who has access to the text would be able to find correlation between events in the 1270 the conflict score by taking the mean of the
936 story and peaks on the graph. However, the authors still stress that such 1271 ratings for each word in a text passage. The more
937 interpretation remains dependent upon the judgement of the reader. Further, other 1272 negative the score is, the higher the conflict is,
938 contributions by the authors are based on the same premises.<a id="fna107" class="fn" href="#fn107" title="Anderson / McMaster 1982; Anderson / McMaster 1993.">[107]</a></p> 1273 and vice versa. Additionally, they plot conflict
939 <p>Alm and Sproat<a id="fna108" class="fn" href="#fn108" title="Alm / Sproat 2005, passim.">[108]</a> present the results of 1274 scores for each consecutive 100 words of a test
940 the emotion annotation task of 22 tales by the Grimm brothers and evaluate patterns 1275 story and provide qualitative analysis of the
941 of emotional story development. They split emotions into <i>positive</i> and <i>negative</i> categories and divide each 1276 peaks. They argue that a reader who has access to
942 story into five parts from which aggregate frequency counts of combined emotion 1277 the text would be able to find correlation between
943 categories are computed. The resulting numbers are plotted on a graph that shows a 1278 events in the story and peaks on the graph.
944 wave-shaped pattern. From this graph, Alm and Sproat argue, one can see that the 1279 However, the authors still stress that such
945 first part of the fairy tales is the least emotional, which is probably due to scene 1280 interpretation remains dependent upon the
946 setting, while the last part shows an increase in positive emotions, which may 1281 judgement of the reader. Further, other
947 signify the happy ending. 1282 contributions by the authors are based on the same
948 </p> 1283 premises.<a id="fna113" class="fn" href="#fn113" title="Anderson / McMaster 1982; Anderson / McMaster 1993.">[113]</a></p>
949 <p>Two other studies by Mohammad<a id="fna109" class="fn" href="#fn109" title="Mohammad 2011, passim; Mohammad 2012, passim.">[109]</a> focus on differences in emotion word density as well as emotional 1284 <p id="pid70"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid70">70</a>]</span>Alm and Sproat<a id="fna114" class="fn" href="#fn114" title="Alm / Sproat 2005.">[114]</a> present the results of the
950 trajectories between books of different genres. Emotion word density is defined as 1285 emotion annotation task of 22 tales by the Grimm
951 a 1286 brothers and evaluate patterns of emotional story
952 number of times a reader will encounter an emotion word on reading every <i>X words</i>. In addition, each text is assigned several emotion 1287 development. They split emotions into <i>positive</i> and <i>negative</i> categories and divide each story
953 scores for each emotion that are calculated as a ratio of words associated with one 1288 into five parts from which aggregate frequency
954 emotion to the total number of emotion words occurring in a text. Both metrics use 1289 counts of combined emotion categories are
955 the <span style="color:#035151"><i>NRC Affective Lexicon</i></span> to find occurrences of emotion 1290 computed. The resulting numbers are plotted on a
956 words. They find that fairy tales have significantly higher <i>anticipation</i>, <i>disgust</i>, <i>joy</i> and 1291 graph that shows a wave-shaped pattern. From this
957 <i>surprise</i> word densities, but lower <i>trust</i> word densities when compared to novels. 1292 graph, Alm and Sproat argue, one can see that the
958 </p> 1293 first part of the fairy tales is the least
959 <p>A work by Klinger et al.<a id="fna110" class="fn" href="#fn110" title="Klinger et&nbsp;al. 2016, passim.">[110]</a> is a case 1294 emotional, which is probably due to scene setting,
960 study in an automatic emotion analysis of Kafka’s <i>Amerika</i> and <i>Das Schloss</i>. The goal of the work is to analyze the development of emotions in both texts 1295 while the last part shows an increase in positive
961 as well as to provide a character-oriented emotion analysis that would reveal 1296 emotions, which may signify the happy ending.
962 specific character traits in both texts. To that end, Klinger et al. develop German 1297 </p>
963 dictionaries of words associated with Ekman’s fundamental emotions plus contempt and 1298 <p id="pid71"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid71">71</a>]</span>Two other studies by Mohammad<a id="fna115" class="fn" href="#fn115" title="Mohammad 2011; Mohammad 2012.">[115]</a> focus on differences in emotion word
964 apply them to both texts in question to automatically detect emotion words. The 1299 density as well as emotional trajectories between
965 results of their analysis for <i>Das Schloss</i> show a striking increase of <i>surprise</i> towards the end 1300 books of different genres. Emotion word density is
966 and a peak of <i>fear</i> shortly after start of chapter 3. In the 1301 defined as a number of times a reader will
967 case of <i>Amerika</i>, the analysis shows that there is a decrease in <i>enjoyment</i> after a peak in chapter 4. 1302 encounter an emotion word on reading every <i>X words</i>. In addition, each text
968 </p> 1303 is assigned several emotion scores for each
969 <p>Yet another work that tracks the flow of emotions in a collection of texts is 1304 emotion that are calculated as a ratio of words
970 presented by Kim et al.<a id="fna111" class="fn" href="#fn111" title="Kim et&nbsp;al. 2017b, passim.">[111]</a> The authors 1305 associated with one emotion to the total number of
971 hypothesize that literary genres can be linked to the development of emotions over 1306 emotion words occurring in a text. Both metrics
972 the course of text. To test this, they collect more than 2,000 books from five genres 1307 use the <span style="color:#035151"><i>NRC Affective
973 (<i>adventure</i>, <i>science fiction</i>, <i>mystery</i>, <i>humor</i> and <i>romance</i>) from Project Gutenberg and identify prototypical emotion shapes for 1308 Lexicon</i></span> to find occurrences of emotion
974 each genre. Each novel in the corpus is split into five consecutive equally-sized 1309 words. They find that fairy tales have
975 segments (following the five-act theory of dramatic acts).<a id="fna112" class="fn" href="#fn112" title="Freytag 1863, passim.">[112]</a> All five genres show close correspondence with regard to <i>sadness</i>, <i>anger</i>, <i>fear</i> and <i>disgust</i>, i.e., a consistent increase of 1310 significantly higher <i>anticipation</i>, <i>disgust</i>, <i>joy</i> and <i>surprise</i> word densities, but
976 these emotions from Act 1 to Act 5, which may correspond to an entertaining 1311 lower <i>trust</i> word densities
977 narrative. <i>Mystery</i> and <i>science fiction</i> 1312 when compared to novels.
978 books show increase in <i>anger</i> towards the end, and <i>joy</i> shows an inverse decreasing pattern from Act 1 to Act 2, 1313 </p>
979 with the exception of <i>humor</i>. 1314 <p id="pid72"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid72">72</a>]</span>A work by Klinger et al.<a id="fna116" class="fn" href="#fn116" title="Klinger et&nbsp;al. 2016.">[116]</a> is a case study in an
980 </p> 1315 automatic emotion analysis of Kafka’s <i>Amerika</i> and <i>Das Schloss</i>. The goal of the work is to analyze the
981 <p>The work by Kakkonen and Galic Kakkonen<a id="fna113" class="fn" href="#fn113" title="Kakkonen / Galic&nbsp;Kakkonen 2011, passim.">[113]</a> aims at supporting the literary analysis of <i>Gothic</i> texts at the sentiment level. The authors introduce a 1316 development of emotions in both texts as well as
982 system called <span style="color:#035151"><i>SentiProfiler</i></span> that generates visual 1317 to provide a character-oriented emotion analysis
983 representations of affective content in such texts and outlines similarities and 1318 that would reveal specific character traits in
984 differences between them, however, without considering the temporal dimension. The 1319 both texts. To that end, Klinger et al. develop
985 <span style="color:#035151"><i>SentiProfiler</i></span> uses <span style="color:#035151"><i>WordNet-Affect</i></span> to 1320 German dictionaries of words associated with
986 derive a list of emotion-bearing words that will be used for analysis. The resulting 1321 Ekman’s fundamental emotions plus contempt and
987 sentiment profiles for the books are used to visualize the presence of sentiment in 1322 apply them to both texts in question to
988 a 1323 automatically detect emotion words. The results of
989 particular document and to compare two different texts. 1324 their analysis for <i>Das Schloss</i> show a striking increase of <i>surprise</i> towards the end and a
990 </p> 1325 peak of <i>fear</i> shortly after
991 </div> 1326 start of chapter 3. In the case of <i>Amerika</i>, the analysis shows that there is a
992 <div id="subchapter"><a name="hd24"> </a><h3> 1327 decrease in <i>enjoyment</i> after
1328 a peak in chapter 4.
1329 </p>
1330 <p id="pid73"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid73">73</a>]</span>A similar study by Schmidt and Burghardt<a id="fna117" class="fn" href="#fn117" title="Schmidt / Burghardt 2018.">[117]</a>
1331 also works on German text – but focuses on the
1332 mostly neglected domain of theater plays, more
1333 concretely the plays by Lessing. They perform an
1334 annotation study and subsequently analyze
1335 different established emotion lexicons to recover
1336 the emotion automatically. The configuration of
1337 the best performing system shows the highest
1338 accuracy of 0.7, while a majority baseline obtains
1339 0.695.
1340 </p>
1341 <p id="pid74"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid74">74</a>]</span>Yet another work that tracks the flow of
1342 emotions in a collection of texts is presented by
1343 Kim et al.<a id="fna118" class="fn" href="#fn118" title="Kim et&nbsp;al. 2017b.">[118]</a> The authors hypothesize that
1344 literary genres can be linked to the development
1345 of emotions over the course of text. To test this,
1346 they collect more than 2,000 books from five
1347 genres (<i>adventure</i>, <i>science fiction</i>, <i>mystery</i>, <i>humor</i> and <i>romance</i>)
1348 from Project Gutenberg and identify prototypical
1349 emotion shapes for each genre. Each novel in the
1350 corpus is split into five consecutive
1351 equally-sized segments (following the five-act
1352 theory of dramatic acts).<a id="fna119" class="fn" href="#fn119" title="Freytag 1863.">[119]</a> All five genres show close
1353 correspondence with regard to <i>sadness</i>, <i>anger</i>, <i>fear</i> and <i>disgust</i>, i.e., a consistent increase of
1354 these emotions from Act 1 to Act 5, which may
1355 correspond to an entertaining narrative. <i>Mystery</i> and <i>science fiction</i> books show increase in <i>anger</i> towards the end, and <i>joy</i> shows an inverse decreasing
1356 pattern from Act 1 to Act 2, with the exception of
1357 <i>humor</i>.
1358 </p>
1359 <p id="pid75"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid75">75</a>]</span>The work by Kakkonen and Galic Kakkonen<a id="fna120" class="fn" href="#fn120" title="Kakkonen / Galic&nbsp;Kakkonen 2011.">[120]</a> aims at supporting the literary
1360 analysis of <i>Gothic</i> texts at
1361 the sentiment level. The authors introduce a
1362 system called <span style="color:#035151"><i>SentiProfiler</i></span>
1363 that generates visual representations of affective
1364 content in such texts and outlines similarities
1365 and differences between them, however, without
1366 considering the temporal dimension. The <span style="color:#035151"><i>SentiProfiler</i></span> uses <span style="color:#035151"><i>WordNet-Affect</i></span> to derive a list
1367 of emotion-bearing words that will be used for
1368 analysis. The resulting sentiment profiles for the
1369 books are used to visualize the presence of
1370 sentiment in a particular document and to compare
1371 two different texts.
1372 </p>
1373 </div><a name="div28"> </a><div id="subchapter"><a name="hd26"> </a><h3>
993 <div style="position:relative;width:90%;">4.5.2 Miscellaneous</div> 1374 <div style="position:relative;width:90%;">4.5.2 Miscellaneous</div>
994 </h3> 1375 </h3>
995 <p>In this section, we review studies that are different in goals and research questions 1376 <p id="pid76"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid76">76</a>]</span>In this section, we review studies that are
996 from the papers presented in previous sections and do not constitute a category on 1377 different in goals and research questions from the
997 their own. 1378 papers presented in previous sections and do not
998 </p> 1379 constitute a category on their own.
999 <p>Koolen<a id="fna114" class="fn" href="#fn114" title="Koolen 2018, passim.">[114]</a> claims that there is a bias among 1380 </p>
1000 readers that put works by female authors on par with »women’s books«, which, as 1381 <p id="pid77"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid77">77</a>]</span>Koolen<a id="fna121" class="fn" href="#fn121" title="Koolen 2018.">[121]</a> claims that there is a bias among
1001 stated by the author, tend to be perceived as of lower literary quality. She 1382 readers that put works by female authors on par
1002 investigates how much »women’s books« (here, <i>romantic</i> novels 1383 with »women’s books«, which, as stated by the
1003 written by women) differ from novels perceived as literary (female and male-authored 1384 author, tend to be perceived as of lower literary
1004 literary fiction). The corpus used in the study is a collection of European and 1385 quality. She investigates how much »women’s books«
1005 North-American novels translated into Dutch. Koolen uses a Dutch version of the <i>Linguistic Inquiry</i> and <span style="color:#035151"><i>Word Count</i></span>,<a id="fna115" class="fn" href="#fn115" title="Boot et&nbsp;al. 2017.">[115]</a> a dictionary that contains content and sentiment-related categories 1386 (here, <i>romantic</i> novels
1006 of words to count the number of words from different categories in each type of 1387 written by women) differ from novels perceived as
1007 fiction. Her analysis shows that romantic novels contain more positive emotions and 1388 literary (female and male-authored literary
1008 words pertaining to friendship than in literary fiction. However, female-authored 1389 fiction). The corpus used in the study is a
1009 literary novels and male-authored ones do not significantly differ on any category. 1390 collection of European and North-American novels
1010 1391 translated into Dutch. Koolen uses a Dutch version
1011 </p> 1392 of the <i>Linguistic Inquiry</i> and <span style="color:#035151"><i>Word
1012 <p>Kraicer and Piper<a id="fna116" class="fn" href="#fn116" title="Kraicer / Piper 2019, passim.">[116]</a> explore the 1393 Count</i></span>,<a id="fna122" class="fn" href="#fn122" title="Boot et&nbsp;al. 2017.">[122]</a> a dictionary that contains content
1013 women’s place within contemporary fiction starting from the premise that there is 1394 and sentiment-related categories of words to count
1014 a 1395 the number of words from different categories in
1015 near ubiquitous underrepresentation and decentralization of women. As a part of their 1396 each type of fiction. Her analysis shows that
1016 analysis, Kraicer and Piper use sentiment scores to look at social balance and 1397 romantic novels contain more positive emotions and
1017 »antagonism«, i.e., how different gender pairings influence positive and negative 1398 words pertaining to friendship than in literary
1018 language surrounding the co-occurrence of characters (using the sentiment dictionary 1399 fiction. However, female-authored literary novels
1019 presented by Liu<a id="fna117" class="fn" href="#fn117" title="Liu et&nbsp;al. 2010, passim.">[117]</a> to calculate a 1400 and male-authored ones do not significantly differ
1020 sentiment score for a character pair). Having analyzed a set of 26,450 characters 1401 on any category.
1021 from 1,333 novels published between 2001 and 2015, the authors find that sentiment 1402 </p>
1022 scores give little indication that the character’s gender has an effect on the state 1403 <p id="pid78"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid78">78</a>]</span>Kraicer and Piper<a id="fna123" class="fn" href="#fn123" title="Kraicer / Piper 2019.">[123]</a> explore the women’s place
1023 of social balance. 1404 within contemporary fiction starting from the
1024 </p> 1405 premise that there is a near ubiquitous
1025 <p>Morin and Acerbi<a id="fna118" class="fn" href="#fn118" title="Morin / Acerbi 2017, passim.">[118]</a> focus on 1406 underrepresentation and decentralization of women.
1026 larger-scale data spanning a hundred thousand of books. The goal of their study is 1407 As a part of their analysis, Kraicer and Piper use
1027 to 1408 sentiment scores to look at social balance and
1028 understand how emotionality of written texts changed throughout the centuries. Having 1409 »antagonism«, i.e., how different gender pairings
1029 collected 307,527 books written between 1900 and 2000 from the <a href="http://storage.googleapis.com/books/ngrams/books/datasetsv2.html" target="_blank">Google Books 1410 influence positive and negative language
1030 corpus</a><a id="fna119" class="fn" href="#fn119" title="Google Books Ngram Viewer 2012.">[119]</a> they collect, for each 1411 surrounding the co-occurrence of characters (using
1031 year, the total number of case-insensitive occurrences of emotion terms that are 1412 the sentiment dictionary presented by Liu<a id="fna124" class="fn" href="#fn124" title="Liu et&nbsp;al. 2010.">[124]</a> to
1032 found under positive and negative taxonomies of <span style="color:#035151"><i>LIWC</i></span> 1413 calculate a sentiment score for a character pair).
1033 dictionary.<a id="fna120" class="fn" href="#fn120" title="Pennebaker et&nbsp;al. 2007.">[120]</a> The main findings 1414 Having analyzed a set of 26,450 characters from
1034 of their research show that emotionality (both <i>positive</i> and 1415 1,333 novels published between 2001 and 2015, the
1035 <i>negative</i> emotions) declines with time, and this decline is 1416 authors find that sentiment scores give little
1036 driven by the decrease in usage of positive vocabulary. Morin and Acerbi remind us 1417 indication that the character’s gender has an
1037 that the <i>Romantic</i> period was dominated by emotionality in 1418 effect on the state of social balance.
1038 writing, which could be the effect of a group of writers who wrote above the mean. 1419 </p>
1039 If 1420 <p id="pid79"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid79">79</a>]</span>Morin and Acerbi<a id="fna125" class="fn" href="#fn125" title="Morin / Acerbi 2017.">[125]</a> focus on larger-scale data
1040 one assumes that each new writer tends to copy the emotional style of their 1421 spanning a hundred thousand of books. The goal of
1041 predecessors, then writers at one point of time are disproportionally influenced by 1422 their study is to understand how emotionality of
1042 this group of above-the-mean writers. However, this trend does not last forever and, 1423 written texts changed throughout the centuries.
1043 sooner or later, the trend reverts to the mean, as each writer reverts to a normal 1424 Having collected 307,527 books written between
1044 level of emotionality. 1425 1900 and 2000 from the <a href="http://storage.googleapis.com/books/ngrams/books/datasetsv2.html" target="_blank">Google Books corpus</a><a id="fna126" class="fn" href="#fn126" title="Google Books Ngram Viewer 2012.">[126]</a> they
1045 </p> 1426 collect, for each year, the total number of
1046 <p>An earlier work<a id="fna121" class="fn" href="#fn121" title="Bentley et&nbsp;al. 2014, passim.">[121]</a> written in 1427 case-insensitive occurrences of emotion terms that
1047 collaboration with <span style="color:#035151"><i>Acerbi</i></span> provides a somewhat different 1428 are found under positive and negative taxonomies
1048 approach and interpretation of the problem of the decline in positive vocabulary in 1429 of <span style="color:#035151"><i>LIWC</i></span> dictionary.<a id="fna127" class="fn" href="#fn127" title="Pennebaker et&nbsp;al. 2007.">[127]</a>
1049 English books of the twentieth century. Using the same dataset and lexical resources 1430 The main findings of their research show that
1050 (plus <span style="color:#035151"><i>WordNet-Affect</i></span>) Bentley et al. find a strong correlation 1431 emotionality (both <i>positive</i>
1051 between expressed negative emotions and the <span style="color:#035151"><i>U.S. economic misery 1432 and <i>negative</i> emotions)
1052 index</i></span>, which is especially strong for the books written during and after 1433 declines with time, and this decline is driven by
1053 the World War I (1918), the Great Depression (1935), and the energy crisis (1975). 1434 the decrease in usage of positive vocabulary.
1054 However, in the present study,<a id="fna122" class="fn" href="#fn122" title="Morin / Acerbi 2017, passim.">[122]</a> the 1435 Morin and Acerbi remind us that the <i>Romantic</i> period was dominated
1055 authors argue that the extent to which positive emotionality correlates with 1436 by emotionality in writing, which could be the
1056 subjective well-being is a debatable issue. Morin and Acerbi provide more possible 1437 effect of a group of writers who wrote above the
1057 reasons for this effect as well as detailed statistical analysis of the data, so we 1438 mean. If one assumes that each new writer tends to
1058 refer the reader to the original paper for more information. 1439 copy the emotional style of their predecessors,
1440 then writers at one point of time are
1441 disproportionally influenced by this group of
1442 above-the-mean writers. However, this trend does
1443 not last forever and, sooner or later, the trend
1444 reverts to the mean, as each writer reverts to a
1445 normal level of emotionality.
1446 </p>
1447 <p id="pid80"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid80">80</a>]</span>An earlier work<a id="fna128" class="fn" href="#fn128" title="Bentley et&nbsp;al. 2014.">[128]</a> written in collaboration with
1448 Acerbi provides a somewhat different approach and
1449 interpretation of the problem of the decline in
1450 positive vocabulary in English books of the
1451 twentieth century. Using the same dataset and
1452 lexical resources (plus <span style="color:#035151"><i>WordNet-Affect</i></span>) Bentley et al. find a
1453 strong correlation between expressed negative
1454 emotions and the <span style="color:#035151"><i>U.S. economic
1455 misery index</i></span>, which is especially strong
1456 for the books written during and after the World
1457 War I, the Great Depression, and the energy crisis
1458 in the 1970s. However, in the present study,<a id="fna129" class="fn" href="#fn129" title="Morin / Acerbi 2017.">[129]</a> the
1459 authors argue that the extent to which positive
1460 emotionality correlates with subjective well-being
1461 is a debatable issue. Morin and Acerbi provide
1462 more possible reasons for this effect as well as
1463 detailed statistical analysis of the data, so we
1464 refer the reader to the original paper for more
1465 information.
1059 </p> 1466 </p>
1060 <div class="medium"> 1467 <div class="medium">
1061 <div class="field-item even" rel="og:image rdfs:seeAlso" resource="../medium1"><a href="http://www.zfdg.de/sites/default/files/medien/emotion_analysis_2019_003.png" title="Tab. 1: Summary of characteristics of methods used in the papers reviewed in this survey. Download as PDF. [Kim / Klinger 2019]" rel="gallery-node" class="colorbox"><img style="max-height:450px!important" class="artikel" alt="Tab. 1: Summary of characteristics of methods used in the papers reviewed&#xA; in this survey. Download as PDF. [Kim / Klinger 2019]" id="emotion_analysis_2019_003" src="http://www.zfdg.de/sites/default/files/styles/medium_in_artikel/emotion_analysis_2019_003.png"></a></div> 1468 <div class="field-item even" rel="og:image rdfs:seeAlso" resource="../medium1"><a href="http://www.zfdg.de/sites/default/files/medien/emotion_analysis_2019_003.png" title="Tab. 1: Summary of characteristics of methods used in the papers reviewed in this survey. Download as PDF. [Kim / Klinger 2021]" rel="gallery-node" class="colorbox"><img style="max-height:450px!important" class="artikel" alt="Tab. 1: Summary of characteristics of&#xA; methods used in the papers reviewed in this survey. Download as PDF.&#xA; [Kim / Klinger 2021]" id="emotion_analysis_2019_003" src="http://www.zfdg.de/sites/default/files/styles/medium_in_artikel/emotion_analysis_2019_003.png"></a></div>
1062 <div class="img_desc"><a href="#abb3">Tab. 1</a>: Summary of characteristics of methods used in the papers reviewed 1469 <div class="img_desc"><a href="#abb3">Tab. 1</a>: Summary of characteristics of
1063 in this survey. Download as <a href="http://www.zfdg.de/files/table_zfdg_klinger.pdf">PDF</a>. [Kim / Klinger 2019]<a href="#emotion_analysis_2019_003"></a></div> 1470 methods used in the papers reviewed in this survey. Download as <a href="https://www.zfdg.de/files/table_zfdg_klinger.pdf">PDF</a>.
1064 </div> 1471 [Kim / Klinger 2021]<a href="#emotion_analysis_2019_003"></a></div>
1065 </div> 1472 </div>
1066 </div> 1473 </div>
1067 </div> 1474 </div>
1068 <div id="chapter"><a name="hd25"> </a><h2> 1475 </div><a name="div29"> </a><div id="chapter"><a name="hd27"> </a><h2>
1069 <div style="position:relative;width:90%;">5 Discussion and Conclusion</div> 1476 <div style="position:relative;width:90%;">5 Discussion and Conclusion</div>
1070 </h2> 1477 </h2>
1071 <p>We have shown throughout this survey that there is a growing interest in sentiment 1478 <p id="pid81"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid81">81</a>]</span>We have shown throughout this survey that there is a growing interest in
1072 and emotion analysis within digital humanities. Given the fact that DH have emerged 1479 sentiment and emotion analysis within computational literary studies as one
1073 into a thriving science within the past decade, it may safely be said that this 1480 main field of digital humanities. Given the fact that DH have emerged into a
1074 direction of research is relatively new. At the same time, the research in sentiment 1481 thriving science within the past decade, it may safely be said that this
1075 analysis started in computational linguistic more than two decades ago and is 1482 direction of research is relatively new. It further constitutes an
1076 nowadays an established field that has dedicated workshops and tracks in the main 1483 interesting field that connects literary studies and computational
1077 computational linguistics conferences. Moreover, a recent meta-study by Mäntylä et 1484 linguistics.
1078 al.<a id="fna123" class="fn" href="#fn123" title="Mäntylä et&nbsp;al. 2018, passim.">[123]</a> shows that the number of 1485 </p>
1079 papers in sentiment analysis is rapidly increasing each year. Indeed, the topic has 1486 <p id="pid82"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid82">82</a>]</span>In computational linguistics, sentiment analysis started more than two
1080 not yet outrun itself and we should not expect to see it vanishing within the next 1487 decades ago and is nowadays an established field that has dedicated
1081 decade or two, provided that no significant paradigm shift in the computational 1488 workshops and tracks in the main conferences. Moreover, a recent meta-study
1082 sciences takes place. One may wonder whether the same applies to sentiment analysis 1489 by Mäntylä et al.<a id="fna130" class="fn" href="#fn130" title="Mäntylä et&nbsp;al. 2018.">[130]</a> shows
1083 in digital humanities scholarship. Will the interest in the topic grow continuously 1490 that the number of papers in sentiment analysis is rapidly increasing each
1084 or will it rally to the peak and vanish in a few years? 1491 year. Indeed, the topic has not yet outrun itself and we should not expect
1085 </p> 1492 to see it vanishing within the next decade or two. In addition, there are
1086 <p>There is no decisive answer. The popularity of sentiment analysis may have reached 1493 still many open challenges. For each novel representation-learning approach,
1087 a 1494 the question arises how sentiment concepts can be approprietly included. For
1088 peak but is far from fading. Application-wise, not a lot has changed during the past 1495 most languages in the world the number of resources is low and it is not
1089 years: researchers are still interested in predicting sentiment and emotion from text 1496 even known if established approaches could simply be transferred. To
1090 for different purposes. If anything has changed, it is methodology. Early research 1497 leverage these issues, research on multilingual methods that induce models
1091 in 1498 in resource-scarce environments is an interesting modern direction, and a
1092 sentiment analysis relied on word polarity and specific dictionaries. Modern 1499 promising and rewarding field. All these developments on machine learning
1093 state-of-the-art approaches rely on word embeddings and deep learning architectures. 1500 models, domain adaptation, pretraining and fine-tuning will also be
1094 Having started with simple polarity detection, contemporary sentiment analysis has 1501 beneficial for the digital humanities, but we cannot expect that all
1095 advanced to a more nuanced analysis of sentiments and emotions. 1502 particular challenges that arise from research questions in literary studies
1096 </p> 1503 will be solved in this field that focuses on generalizable methods.
1097 <p>The situation is somewhat different in digital humanities research. Most of the works 1504 </p>
1098 rely on affective lexicons and word counts, a technique for detecting emotions in 1505 <p id="pid83"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid83">83</a>]</span>Digital humanties has specific needs that cannot be readily addressed by
1099 literary text first used by Anderson and McMaster in 1982.<a id="fna124" class="fn" href="#fn124" title="Anderson / McMaster 1982, passim.">[124]</a> Even the most recent works base the 1506 existing methods or those that are developed in the future, in computational
1100 interpretation of the results on the use of dictionaries and counts of 1507 linguistics, machine learning, and computer science in general. As we have
1101 emotion-bearing words in a text, passage, or sentence. In fact, around 70% of the 1508 seen in this survey, most of the works rely on affective lexicons and word
1102 papers we discussed in <a title="" href="#hd8">Section 4</a> substantially rely on the use of various lexical 1509 counts, a technique for detecting emotions in literary text first used by
1103 resources for detecting emotions (see <a title="" href="#emotion_analysis_2019_003"><span class="medium">Table 1</span></a> for a summary of methods used in the 1510 Anderson and McMaster in 1982.<a id="fna131" class="fn" href="#fn131" title="Anderson / McMaster 1982.">[131]</a> Even the most recent works base the interpretation of the
1104 reviewed papers). We have discussed some limitations of this approach in <a title="" href="#hd12">Section 4.2</a>. 1511 results on the use of dictionaries and counts of emotion-bearing words in a
1105 Let us reiterate its weakness with the following small example. Consider the sentence 1512 text, passage, or sentence. In fact, around 70 % of the papers we discussed
1106 ›Jack was afraid of John because John held a knife in his hand‹. Assuming a 1513 in <a title="" href="#hd10">section 4</a> substantially rely on the
1107 dictionary of emotion-bearing words is used, the sentence can be categorized as 1514 use of various lexical resources for detecting emotions. We identify a set
1108 expressing <i>fear</i>, because of the two strong fear markers, <i>afraid</i> and <i>knife</i>. Indeed, the sentence 1515 of particular challenges that hold for digital humanities and computational
1109 does express <i>fear</i>. But does it do it equally for Jack and 1516 literary studies and that are presumable reasons for that choice.
1110 John? The answer is no: Jack is the one who is afraid and John holding a knife is 1517 </p>
1111 the 1518 <p id="pid84"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid84">84</a>]</span><i>The object of research is the central element. </i>In
1112 reason for Jack being afraid. Let us assume that a researcher is interested in the 1519 contrast to computational linguistics, the goal of digital humanities is not
1113 emotion analysis of a book that contains thousands of sentences expressing emotions 1520 to develop generalizable methods. The goal is, instead, to develop those
1114 in different ways: some sentences describe characters who feel emotions just as in 1521 methods that are helpful for a particular research question; and in contrast
1115 the sentence above, some are narrator’s digressions filled with emotions, some 1522 to computational linguistics, this includes tasks that only very few people
1116 contain emotion-bearing words (<i>knife</i>, <i>baby</i>) but do not in fact express the same emotion in any given context. No 1523 work on. It would be a huge advantage if those methods could be generalized
1117 doubt, a dictionary and count-based approach will be helpful in understanding the 1524 and reused, however, it is not a primary goal. Instead, an emotion analysis
1118 distribution of the emotion lexicon throughout the story. But is it enough for the 1525 method for a particular scholar who analyzes texts from a particular subset,
1119 interpretation? Can hermeneutics, in its traditional form, make use of such 1526 for instance genre, period, or author needs to work well for this subset. It
1120 knowledge? Barely. In fact, some of the works that we reviewed pinpoint that the 1527 might not be feasable to develop sophisticated deep learning methods for
1121 surface affective value of the words does not always align with their more nuanced 1528 each of these approaches, but just to be used once.
1122 affective meaning and that sentiment analysis tools make mistakes when classifying 1529 </p>
1123 a 1530 <p id="pid85"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid85">85</a>]</span><i>Transparency of the computational method is not a bonus;
1124 text as emotional or not.<a id="fna125" class="fn" href="#fn125" title="Reed 2018, passim.">[125]</a> If so, how reliable 1531 it is a crucial property.</i> In digital humanities, research is often
1125 is the interpretation? In other words, what kind of interpretation should we expect 1532 exploratory. The application of an existing method on a corpus can lead to
1126 from the sentiment and emotion analysis research in the DH community? 1533 new findings, but it is common that an interactive application of a method
1127 </p> 1534 to explore a phenomenon is even more promising. Such interactive application
1128 <p>We do not have a ready answer to that question. At the one extreme, there is 1535 requires full control by the user in real time – and that is something that
1129 traditional hermeneutics, the examples of which are presented in a <a title="" href="#hd7">Section 3</a>. At the 1536 pretrained deep neural methods cannot (yet) provide. However, emotion
1130 other extreme, there is interpretation in the form of ›Author A writes with more 1537 lexicons that point to particular aspects in the text in a transparent
1131 emotion than author B because the numbers say so‹. We do, however, suggest that a 1538 manner do, despite of their disadvantages.
1132 balance should be made somewhere between these two extremes. Even as simple as it 1539 </p>
1133 is, 1540 <p id="pid86"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid86">86</a>]</span><i>Computational expertise is not sufficient in an
1134 the approach of detecting sentiment and emotion-related words can be used to deliver 1541 interdisciplinary research field. </i>In computational research
1135 a high-quality interpretation such as in Heuser et al.<a id="fna126" class="fn" href="#fn126" title="Heuser et&nbsp;al. 2016, passim.">[126]</a> or Morin and Acerbi.<a id="fna127" class="fn" href="#fn127" title="Morin and Acerbi 2017, passim.">[127]</a> However, we note again that there are still limits posed by the 1542 disciplines, a minimum amount of understanding of the respective domain is
1136 simplicity of this approach. 1543 helpful but not necessarily (always) required. Particularly in recent years,
1137 </p> 1544 with the development of end-to-end learning methods that hardly explain
1138 <p>This leads us to an outline of the reality of sentiment analysis research in digital 1545 decisions, it became common to purely rely on performance measures (though
1139 humanities: the methods of sentiment analysis used by some of the DH scholars 1546 this changes with recent research on explainable artificial intelligence).
1140 nowadays have gone or are almost extinct among computational linguists. This in turn 1547 In contrast, in computational literary studies, knowledge of the domain is
1141 affects the quality of the interpretation. 1548 required. Without it, research questions cannot be answered. This is not a
1142 </p> 1549 unique property of digital humanities as an interdisciplnary field. However,
1143 <p>However, we admit that this criticism may be unfair. In fact, there is a possible 1550 it is particularly challenging here, given its recent growth, fast
1144 reason why DH researchers have taken this approach to sentiment analysis. Digital 1551 development, and also the differences in the research culture between
1145 humanities are still being formed as an independent discipline and it is easier to 1552 humanities and computer science (which are arguably smaller between, for
1146 form something new in a step-by-step fashion. Resorting to a metaphor from the 1553 instance, natural sciences and computer science, to which fields like
1147 construction world, one should first learn how to stack single bricks to build a wall 1554 computational chemistry or bioinformatics belong).
1148 rather than starting from the design of a communications system. It is necessary to 1555 </p>
1149 make sure that appropriate tools and methods are chosen instead of using what proved 1556 <p id="pid87"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid87">87</a>]</span>This leads to a set of challenges that need to be addressed, while developing
1150 to be successful in other domains without reflection. It is true that much digital 1557 methods further. In contrast to most emotion analysis work in other domains
1151 humanities research (especially dealing with text) uses the methods of text analysis 1558 (like social media or news), the unit of analysis should be larger. It is
1152 that were in fashion in computational linguistic twenty years ago. One may argue that 1559 not sufficient to only analyze sentences in isolation (or even just words).
1153 new research in digital humanities should start with the <span style="color:#035151"><i>state-of-the-art methods</i></span>. Indeed, some arguments that methodology is at 1560 Instead, the overall development of characters, the story line as a whole
1154 the root of the interpretation have already been made.<a id="fna128" class="fn" href="#fn128" title="Da 2019, passim.">[128]</a> So, if there is anything that digital humanities can learn from 1561 need to be considered. This is a research direction that hardly received any
1155 computational linguistics, it is that methodology cannot stall. What really matters 1562 attention yet; presumably because of technical challenges, but likely also
1156 for digital humanities is interpretation, and if methodology is not going forward, 1563 due to the lack of annotated corpora that would be required to contain
1157 the interpretation is not either. 1564 annotations on different levels. Further, these annotations need particular
1158 </p> 1565 expertise from the annotators. It is not feasible to show an entire book to
1159 </div> 1566 workers on a crowdsourcing platform to receive annotations on fine-grained
1160 <div id="chapter"><a name="hd26"> </a><h2> 1567 levels (for characters and their developments). Therefore, for domains of
1568 interest, we point out that the development of corpora in computational
1569 literary studies are expected to be more expensive and will take longer than
1570 in other fields in which emotion analysis is applied.
1571 </p>
1572 <p id="pid88"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid88">88</a>]</span>Finally, we believe that the integration of psychological models into
1573 computational approaches in literature studies is important. Literature
1574 contains representations of whole worlds, the depictions are more
1575 comprehensive than in news articles or social media. This also requires a
1576 deeper understanding of described social processes and (imagined) mental
1577 states.
1578 </p>
1579 <p id="pid89"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid89">89</a>]</span>And finally, the role of the experiencer of an emotion needs to be considered
1580 more than in other fields. While on Twitter analysis, we typically care
1581 about the emotion that the author of a message felt while writing it, we
1582 typically do not care about the emotion of the author of a novel, while
1583 writing it.<a id="fna132" class="fn" href="#fn132" title="Oberländer et al. 2020.">[132]</a> Instead, we
1584 are faced with the more challenging task to attribute emotions to characters
1585 or even infer the emotions that might be developed by readers of a text.
1586 </p>
1587 <p id="pid90"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid90">90</a>]</span>In summary, we believe that the field of emotion analysis for literary
1588 studies has still space for research in multiple directions. The main
1589 challenge will be to identify the particular challenges of literare and
1590 develop methods for these text genres, instead of using existing methods
1591 that have developed with the purpose in mind of being generalizing across
1592 application areas.
1593 </p>
1594 </div><a name="div30"> </a><div id="chapter"><a name="hd28"> </a><h2>
1161 <div style="position:relative;width:90%;">Acknowledgements</div> 1595 <div style="position:relative;width:90%;">Acknowledgements</div>
1162 </h2> 1596 </h2>
1163 <p> 1597 <p id="pid91"><span style="float: right; padding: .2em; color: #999; border: 1px solid #ccc; background-color: #eee; margin-right: -80px;">[<a href="#pid91">91</a>]</span>We thank Laura Ana Maria Oberländer, Sebastian Padó, and Enrica Troiano for
1164 We thank Laura Ana Maria Bostan, Sebastian Padó, and Enrica Troiano 1598 fruitful discussions and the ZfDG team for their help in preparation of this
1165 for fruitful discussions and the ZfDG team for their help in preparation of this 1599 article. This research has been conducted within the <a href="www.creta.uni-stuttgart.de\" target="_blank">CRETA</a> project which is funded by the German Ministry for
1166 article. This research has been conducted within the <a href="http:\www.creta. uni-stuttgart.de" target="_blank">CRETA</a> project which is funded by the German Ministry for Education and 1600 Education and Research (BMBF) and partially funded by the German Research
1167 Research (BMBF) and partially funded by the German Research Council (DFG), projects 1601 Council (DFG), projects SEAT (Structured Multi-Domain Emotion Analysis from
1168 SEAT (Structured Multi-Domain Emotion Analysis from Text, KL 2869/1-1). 1602 Text, KL 2869/1-1). We further thank the anonymous reviewers for their
1603 helpful comments on an earlier version of this article.
1169 </p> 1604 </p>
1173 <hr><a name="footnotes"></a><div class="footnote"> 1608 <hr><a name="footnotes"></a><div class="footnote">
1174 <h2>Footnotes</h2> 1609 <h2>Fußnoten</h2>
1175 <ul class="footnote"> 1610 <ul class="footnote">
1178 </div> 1613 </div>
1179 <div class="footnote3"><a title="Bing Liu: Sentiment Analysis: mining opinions, sentiments, and emotions. New York, NY 2015." href="#liu_opinions_2015">Liu 2015</a>, p.2. 1614 <div class="footnote3"><a title="Bing Liu: Sentiment Analysis: mining opinions, sentiments, and emotions. New York, NY 2015." href="#liu_opinions_2015">Liu 2015</a>,
1615 p. 2.
1180 </div> 1616 </div>
1183 </div> 1619 </div>
1184 <div class="footnote3"><a title="Mohammad Soleymani / David Garcia / Brendan Jou / Björn Schuller / Shih-Fu Chang / Maja Pantic: A survey of multimodal sentiment analysis. In: Image and Vision Computing 65 (2017), pp. 3–14." href="#soleymani_survey_2017">Soleymani et&nbsp;al. 2017</a>. 1620 <div class="footnote3"><a title="Mohammad Soleymani / David Garcia / Brendan Jou / Björn Schuller / Shih-Fu Chang / Maja Pantic: A survey of multimodal sentiment analysis. In: Image and Vision Computing 65 (2017), pp. 3–14." href="#soleymani_survey_2017">Soleymani et&nbsp;al.
1621 2017</a>.
1185 </div> 1622 </div>
1188 </div> 1625 </div>
1189 <div class="footnote3"><a title="Klaus&nbsp;R. Scherer: What are emotions? And how can they be measured? In: Social Science Information 44 (2005), i. 4, pp. 695729." href="#scherer_emotions_2005">Scherer 2005</a>, p. 695. 1626 <div class="footnote3"><a title="Janyce Wiebe / Theresa Wilson / Rebecca Bruce / Matthew Bell / Melanie Martin: Learning Subjective Language. In: Computational Linguistics 30 (2004), pp. 277308." href="#wiebe_language_2004">Wiebe et al. 2004</a>.
1190 </div> 1627 </div>
1193 </div> 1630 </div>
1194 <div class="footnote3"><a title="Andrea Scarantino: The Phylosophy of Emotions and Its Impact on Affective Sciences. In: Handbook of emotions. Ed. by Lisa Feldman Barret / Michael Lewis / Jeannette M. Haviland-Jones. 4. edition. New York, NY et al. 2016. pp. 349." href="#scarantino_phylosophy_2016">Scarantino 2016</a>, p. 36. 1631 <div class="footnote3"><a title="Klaus&nbsp;R. Scherer: What are emotions? And how can they be measured? In: Social Science Information 44 (2005), i. 4, pp. 695729." href="#scherer_emotions_2005">Scherer 2005</a>, p. 1.
1195 </div> 1632 </div>
1198 </div> 1635 </div>
1199 <div class="footnote3"><a title="John&nbsp;D. Mayer / Richard&nbsp;D. Roberts / Sigal&nbsp;G. Barsade: Human abilities: Emotional intelligence. In: Annual Review of Psychology 59 (2008), i. 1, pp. 507536." href="#mayer_abilities_2008">Mayer et&nbsp;al. 2008</a>, p. 510. 1636 <div class="footnote3"><a title="Andrea Scarantino: The Philosophy of Emotions and Its Impact on Affective Sciences. In: Handbook of emotions. Ed. by Lisa Feldman Barret / Michael Lewis / Jeannette M. Haviland-Jones. 4. edition. New York, NY et al. 2016. pp. 349." href="#scarantino_philosophy_2016">Scarantino 2016</a>, p. 36.
1200 </div> 1637 </div>
1203 </div> 1640 </div>
1641 <div class="footnote3"><a title="John&nbsp;D. Mayer / Richard&nbsp;D. Roberts / Sigal&nbsp;G. Barsade: Human abilities: Emotional intelligence. In: Annual Review of Psychology 59 (2008), i. 1, pp. 507–536." href="#mayer_abilities_2008">Mayer et&nbsp;al. 2008</a>, p. 2.
1642 </div>
1643 </li><br><li class="footnote">
1644 <div class="footnote2" id="fn7" href="#fna7">[<a href="#fna7">7</a>]
1645 </div>
1204 <div class="footnote3"><a title="Nan&nbsp;Z. Da: The computational case against computational literary studies. In: Critical Inquiry 45 (2019), i. 3, pp. 601–639." href="#da_case_2019">Da 2019</a>, p. 602. 1646 <div class="footnote3"><a title="Nan&nbsp;Z. Da: The computational case against computational literary studies. In: Critical Inquiry 45 (2019), i. 3, pp. 601–639." href="#da_case_2019">Da 2019</a>, p. 602.
1206 </li><br><li class="footnote"> 1648 </li><br><li class="footnote">
1207 <div class="footnote2" id="fn7" href="#fna7">[<a href="#fna7">7</a>] 1649 <div class="footnote2" id="fn8" href="#fna8">[<a href="#fna8">8</a>]
1208 </div> 1650 </div>
1211 </li><br><li class="footnote"> 1653 </li><br><li class="footnote">
1212 <div class="footnote2" id="fn8" href="#fna8">[<a href="#fna8">8</a>]
1213 </div>
1214 <div class="footnote3"><a title="David&nbsp;Lowell Hoover / Jonathan Culpeper / Kieran O’Halloran: Digital literary studies: Corpus Approaches to Poetry, Prose, and Drama. New York, NY 2014." href="#hoover_studies_2014">Hoover et&nbsp;al. 2014</a>.
1215 </div>
1216 </li><br><li class="footnote">
1217 <div class="footnote2" id="fn9" href="#fna9">[<a href="#fna9">9</a>] 1654 <div class="footnote2" id="fn9" href="#fna9">[<a href="#fna9">9</a>]
1218 </div> 1655 </div>
1219 <div class="footnote3"><a title="Norbert Schwarz: Emotion, cognition, and decision making. In: Cognition &amp; Emotion 14 (2000), i. 4, pp. 433–440." href="#schwarz_emotion_2000">Schwarz 2000</a>, p. 433. 1656 <div class="footnote3"><a title="David&nbsp;Lowell Hoover / Jonathan Culpeper / Kieran O’Halloran: Digital literary studies: Corpus Approaches to Poetry, Prose, and Drama. New York, NY 2014." href="#hoover_studies_2014">Hoover et&nbsp;al.
1657 2014</a>.
1220 </div> 1658 </div>
1223 </div> 1661 </div>
1224 <div class="footnote3"><a title="Philip&nbsp;Nicholas Johnson-Laird / Keith Oatley: Emotions in Music, Literature, and Film. In: Handbook of emotions. Ed. by Lisa Feldman Barret / Michael Lewis / Jeannette M. Haviland-Jones. 4. edition. New York, NY et al. 2016. pp. 82–97." href="#johnson_emotions_2016">Johnson-Laird / Oatley 2016</a>, 1662 <div class="footnote3"> E.g. <a title="Mostafa&nbsp;Al&nbsp;Masum&nbsp;Shaikh / Helmut&nbsp;Prendinger / Mitsuru&nbsp;Ishizuka: A Linguistic Interpretation of the OCC Emotion Model for Affect Sensing from Text. In: Affective Information Processing. Ed. by Jianhua Tao / Tieniu Tan. London 2009." href="#shaikh_interpretation_2009">Shaikh 2009</a>.
1225 passim; <a title="Maja Djikic / Keith Oatley / Sara Zoeterman / Jordan&nbsp;B. Peterson: On being moved by art: How reading fiction transforms the self. In: Creativity Research Journal 21 (2009), i. 1, pp. 24–29." href="#djikic_art_2009">Djikic et&nbsp;al. 2009</a>, passim. 1663
1226 </div> 1664 </div>
1228 <div class="footnote2" id="fn11" href="#fna11">[<a href="#fna11">11</a>] 1666 <div class="footnote2" id="fn11" href="#fna11">[<a href="#fna11">11</a>]
1667 </div>
1668 <div class="footnote3"><a title="Norbert Schwarz: Emotion, cognition, and decision making. In: Cognition &amp; Emotion 14 (2000), i. 4, pp. 433–440." href="#schwarz_emotion_2000">Schwarz 2000</a>,
1669 p. 433.
1670 </div>
1671 </li><br><li class="footnote">
1672 <div class="footnote2" id="fn12" href="#fna12">[<a href="#fna12">12</a>]
1673 </div>
1674 <div class="footnote3"><a title="Philip&nbsp;Nicholas Johnson-Laird / Keith Oatley: Emotions in Music, Literature, and Film. In: Handbook of emotions. Ed. by Lisa Feldman Barret / Michael Lewis / Jeannette M. Haviland-Jones. 4. edition. New York, NY et al. 2016. pp. 82–97." href="#johnson_emotions_2016">Johnson-Laird /
1675 Oatley 2016</a>; <a title="Maja Djikic / Keith Oatley / Sara Zoeterman / Jordan&nbsp;B. Peterson: On being moved by art: How reading fiction transforms the self. In: Creativity Research Journal 21 (2009), i. 1, pp. 24–29." href="#djikic_art_2009">Djikic et&nbsp;al. 2009</a>.
1676 </div>
1677 </li><br><li class="footnote">
1678 <div class="footnote2" id="fn13" href="#fna13">[<a href="#fna13">13</a>]
1229 </div> 1679 </div>
1231 <a title="Patrick&nbsp;Colm Hogan: Fictions and feelings: On the place of literature in the study of emotion. In: Emotion Review 2 (2010), i. 2, pp. 184–195." href="#hogan_fictions_2010">Hogan 2010</a>; 1681 <a title="Patrick&nbsp;Colm Hogan: Fictions and feelings: On the place of literature in the study of emotion. In: Emotion Review 2 (2010), i. 2, pp. 184–195." href="#hogan_fictions_2010">Hogan 2010</a>;
1232 <a title="Patrick&nbsp;Colm Hogan: What Literature Teaches Us about Emotion. New York, NY 2011." href="#hogan_literature_2011">Hogan 2011</a>; 1682 <a title="Patrick&nbsp;Colm Hogan: What Literature Teaches Us about Emotion. New York, NY 2011." href="#hogan_literature_2011">Hogan
1233 <a title="P. Matthijs Bal / Martijn Veltkamp: How does fiction reading influence empathy? An experimental investigation on the role of emotional transportation. In: PLOS ONE 8 (2013), i. 1, p. e55341. Article from 30.01.2013. DOI: 10.1371/journal.pone.0055341" href="#bal_fiction_2013">Bal / Veltkamp 2013</a>; 1683 2011</a>; <a title="P. Matthijs Bal / Martijn Veltkamp: How does fiction reading influence empathy? An experimental investigation on the role of emotional transportation. In: PLOS ONE 8 (2013), i. 1, p. e55341. Article from 30.01.2013. DOI: 10.1371/journal.pone.0055341" href="#bal_fiction_2013">Bal /
1234 <a title="Maja Djikic / Keith Oatley / Mihnea&nbsp;C. Moldoveanu: Reading other minds: Effects of literature on empathy. In: Scientific Study of Literature 3 (2013), i. 1, pp. 28–47." href="#djikic_minds_2013">Djikic et&nbsp;al. 2013</a>; 1684 Veltkamp 2013</a>; <a title="Maja Djikic / Keith Oatley / Mihnea&nbsp;C. Moldoveanu: Reading other minds: Effects of literature on empathy. In: Scientific Study of Literature 3 (2013), i. 1, pp. 28–47." href="#djikic_minds_2013">Djikic et&nbsp;al. 2013</a>; <a title="Dan&nbsp;R. Johnson: Transportation into a story increases empathy, prosocial behavior, and perceptual bias toward fearful expressions. In: Personality and Individual Differences 52 (2012), i. 2, pp. 150–155." href="#johnson_transportation_2012">Johnson 2012</a>; <a title="Dalya Samur / Mattie Tops / Sander&nbsp;L. Koole: Does a single session of reading literary fiction prime enhanced mentalising performance? Four replication experiments of Kidd and Castano (2013). In: Cognition &amp; Emotion 32 (2018), pp. 130–144." href="#samur_session_2018">Samur et&nbsp;al.
1235 <a title="Dan&nbsp;R. Johnson: Transportation into a story increases empathy, prosocial behavior, and perceptual bias toward fearful expressions. In: Personality and Individual Differences 52 (2012), i. 2, pp. 150–155." href="#johnson_transportation_2012">Johnson 2012</a>; 1685 2018.</a></div>
1236 <a title="Dalya Samur / Mattie Tops / Sander&nbsp;L. Koole: Does a single session of reading literary fiction prime enhanced mentalising performance? Four replication experiments of Kidd and Castano (2013). In: Cognition &amp; Emotion 32 (2018), pp. 130–144." href="#samur_session_2018">Samur et&nbsp;al. 2018.</a></div>
1237 </li><br><li class="footnote">
1238 <div class="footnote2" id="fn12" href="#fna12">[<a href="#fna12">12</a>]
1239 </div>
1240 <div class="footnote3"><a title="Dolf Zillmann / Richard&nbsp;T. Hezel / Norman&nbsp;J. Medoff: The effect of affective states on selective exposure to televised entertainment fare. In: Journal of Applied Social Psychology 10 (1980), i. 4, pp. 323–339." href="#zillmann_effect_1980">Zillmann et&nbsp;al. 1980</a>;
1241 <a title="Catherine&nbsp;Sheldrick Ross: Finding without seeking: the information encounter in the context of reading for pleasure. In: Information Processing &amp; Management 35 (1999), i. 6., pp. 783–799." href="#ross_encounter_1999">Ross 1999</a>;
1242 <a title="Jennings Bryant / Dolf Zillmann: Using television to alleviate boredom and stress: Selective exposure as a function of induced excitational states. In: Journal of Broadcasting &amp; Electronic Media 28 (1984), i. 1, pp. 1–20." href="#bryant_television_1984">Bryant / Zillmann 1984</a>;
1243 <a title="Mary&nbsp;Beth Oliver: Tender affective states as predictors of entertainment preference. In: Journal of Communication 58 (2008), i. 1, pp. 40–61." href="#oliver_states_2008">Oliver 2008</a>;
1244 <a title="Raymond&nbsp;A. Mar / Keith Oatley / Maja Djikic / Justin Mullin: Emotion and narrative fiction: Interactive influences before, during, and after reading. In: Cognition &amp; Emotion 25 (2011), i. 5, pp. 818–833." href="#mar_emotion_2011">Mar et&nbsp;al.
1245 2011.</a></div>
1246 </li><br><li class="footnote">
1247 <div class="footnote2" id="fn13" href="#fna13">[<a href="#fna13">13</a>]
1248 </div>
1249 <div class="footnote3"><a title="Plato: Plato in Twelve Volumes. Cambridge, MA 1969. Siehe auch" href="#plato_volumes_1969">Plato 1969</a>
1250 , passim.
1251 </div>
1252 </li><br><li class="footnote"> 1686 </li><br><li class="footnote">
1254 </div> 1688 </div>
1255 <div class="footnote3"><a title="Aristotle: Poetics. Penguin 1996. (= Penguin Classics)" href="#aristotele_poetics_1996">Aristotle 1996</a>, passim. 1689 <div class="footnote3"><a title="Dolf Zillmann / Richard&nbsp;T. Hezel / Norman&nbsp;J. Medoff: The effect of affective states on selective exposure to televised entertainment fare. In: Journal of Applied Social Psychology 10 (1980), i. 4, pp. 323–339." href="#zillmann_effect_1980">Zillmann et&nbsp;al.
1256 </div> 1690 1980</a>; <a title="Catherine&nbsp;Sheldrick Ross: Finding without seeking: the information encounter in the context of reading for pleasure. In: Information Processing &amp; Management 35 (1999), i. 6., pp. 783–799." href="#ross_encounter_1999">Ross
1691 1999</a>; <a title="Jennings Bryant / Dolf Zillmann: Using television to alleviate boredom and stress: Selective exposure as a function of induced excitational states. In: Journal of Broadcasting &amp; Electronic Media 28 (1984), i. 1, pp. 1–20." href="#bryant_television_1984">Bryant / Zillmann 1984</a>; <a title="Mary&nbsp;Beth Oliver: Tender affective states as predictors of entertainment preference. In: Journal of Communication 58 (2008), i. 1, pp. 40–61." href="#oliver_states_2008">Oliver 2008</a>; <a title="Raymond&nbsp;A. Mar / Keith Oatley / Maja Djikic / Justin Mullin: Emotion and narrative fiction: Interactive influences before, during, and after reading. In: Cognition &amp; Emotion 25 (2011), i. 5, pp. 818–833." href="#mar_emotion_2011">Mar et&nbsp;al. 2011.</a></div>
1257 </li><br><li class="footnote"> 1692 </li><br><li class="footnote">
1259 </div> 1694 </div>
1260 <div class="footnote3"><a title="Ronald de&nbsp;Sousa / Andrea Scarantino: Emotion. In: The Stanford Encyclopedia of Philosophy. Ed. by Edward&nbsp;N. Zalta. Stanford, CA 2018. Article from 25.09.2018. [online]" href="#sousa_emotion_2018">De&nbsp;Sousa / Scarantino 2018</a>. 1695 <div class="footnote3"><a title="Plato: Plato in Twelve Volumes. Cambridge, MA 1969. Siehe auch" href="#plato_volumes_1969">Plato 1969</a>.
1261 </div> 1696 </div>
1264 </div> 1699 </div>
1265 <div class="footnote3"><a title="Leo Tolstoy: What is art? And essays on art. Harmondsworth 1962. (= Penguin classics) Siehe auch" href="#tolstoy_art_1962">Tolstoy 1962</a>, passim. 1700 <div class="footnote3"><a title="Aristotle: Poetics. Penguin 1996. (= Penguin Classics)" href="#aristotle_poetics_1996">Aristotle 1996</a>.
1266 </div> 1701 </div>
1269 </div> 1704 </div>
1270 <div class="footnote3"><a title="Clifford&nbsp;W. Anderson / George&nbsp;E. McMaster: Modeling emotional tone in stories using tension levels and categorical states. In: Computers and the Humanities 20 (1986), i. 1, pp. 3–9." href="#anderson_tone_1986">Anderson / McMaster 1986</a>, p. 3; 1705 <div class="footnote3"><a title="Ronald de&nbsp;Sousa / Andrea Scarantino: Emotion. In: The Stanford Encyclopedia of Philosophy. Ed. by Edward&nbsp;N. Zalta. Stanford, CA 2018. Article from 25.09.2018. [online]" href="#sousa_emotion_2018">de&nbsp;Sousa /
1271 <a title="Patrick&nbsp;Colm Hogan: Fictions and feelings: On the place of literature in the study of emotion. In: Emotion Review 2 (2010), i. 2, pp. 184–195." href="#hogan_fictions_2010">Hogan 2010</a>, p. 187; <a title="Andrew Piper / Richard Jean&nbsp;So: Quantifying the weepy bestseller. In: The New Rebublic. Article from 18.12.2015. [online]" href="#piper_bestseller_2015">Piper / 1706 Scarantino 2018</a>.
1272 Jean&nbsp;So 2015</a>.
1273 </div> 1707 </div>
1276 </div> 1710 </div>
1711 <div class="footnote3"><a title="Leo Tolstoy: What is art? And essays on art. Harmondsworth 1962. (= Penguin classics) Siehe auch" href="#tolstoy_art_1962">Tolstoy 1962</a>.
1712 </div>
1713 </li><br><li class="footnote">
1714 <div class="footnote2" id="fn19" href="#fna19">[<a href="#fna19">19</a>]
1715 </div>
1716 <div class="footnote3"><a title="Clifford&nbsp;W. Anderson / George&nbsp;E. McMaster: Modeling emotional tone in stories using tension levels and categorical states. In: Computers and the Humanities 20 (1986), i. 1, pp. 3–9." href="#anderson_tone_1986">Anderson / McMaster
1717 1986</a>, p. 3; <a title="Patrick&nbsp;Colm Hogan: Fictions and feelings: On the place of literature in the study of emotion. In: Emotion Review 2 (2010), i. 2, pp. 184–195." href="#hogan_fictions_2010">Hogan 2010</a>, p. 187; <a title="Andrew Piper / Richard Jean&nbsp;So: Quantifying the weepy bestseller. In: The New Rebublic. Article from 18.12.2015. [online]" href="#piper_bestseller_2015">Piper / Jean&nbsp;So 2015</a>.
1718 </div>
1719 </li><br><li class="footnote">
1720 <div class="footnote2" id="fn20" href="#fna20">[<a href="#fna20">20</a>]
1721 </div>
1277 <div class="footnote3"><a title="Richard&nbsp;A. Lanham: The electronic word: Literary study and the digital revolution. In: New Literary History 20 (1989), i. 2, pp. 265–290." href="#lanham_word_1989">Lanham 1989</a>. 1722 <div class="footnote3"><a title="Richard&nbsp;A. Lanham: The electronic word: Literary study and the digital revolution. In: New Literary History 20 (1989), i. 2, pp. 265–290." href="#lanham_word_1989">Lanham 1989</a>.
1279 </li><br><li class="footnote"> 1724 </li><br><li class="footnote">
1280 <div class="footnote2" id="fn19" href="#fna19">[<a href="#fna19">19</a>]
1281 </div>
1282 <div class="footnote3"><a title="David&nbsp;M. Berry: Introduction: Understanding the digital humanities. In: Understanding digital humanities. Ed. by David M. Berry. Houndmills et al. 2012, pp. 1–20." href="#berry_introduction_2012">Berry 2012</a>; <a title="Susan Schreibman / Ray Siemens / John Unsworth: A New Companion to Digital Humanities. Chichester et al. 2015/2016." href="#schreibman_compainion_2016">Schreibman et&nbsp;al. 2015</a>.
1283 </div>
1284 </li><br><li class="footnote">
1285 <div class="footnote2" id="fn20" href="#fna20">[<a href="#fna20">20</a>]
1286 </div>
1287 <div class="footnote3"><a title="Edward Vanhoutte: The gates of hell: History and definition of digital|humanities|computing. In: Defining Digital Humanities. A Reader. Ed. by Meliss Terras / Julianne Hyhan / Edward Vanhoutte. Farnham 2013, pp. 119–156." href="#vanhoutte_gates_2013">Vanhoutte 2013</a>, p. 142;
1288 <a title="Matthew&nbsp;Lee Jockers / Ted Underwood: Text-mining the humanities. In: A New Companion to Digital Humanities. Ed. by Susan Schreibman / Ray Siemens / John Unsworth. Pondicherry 2016, pp. 291–306." href="#jockers_humanities_2016">Jockers / Underwood
1289 2016</a>, pp. 292f.
1290 </div>
1291 </li><br><li class="footnote">
1292 <div class="footnote2" id="fn21" href="#fna21">[<a href="#fna21">21</a>] 1725 <div class="footnote2" id="fn21" href="#fna21">[<a href="#fna21">21</a>]
1726 </div>
1727 <div class="footnote3"><a title="David&nbsp;M. Berry: Introduction: Understanding the digital humanities. In: Understanding digital humanities. Ed. by David M. Berry. Houndmills et al. 2012, pp. 1–20." href="#berry_introduction_2012">Berry 2012</a>;
1728 <a title="Susan Schreibman / Ray Siemens / John Unsworth: A New Companion to Digital Humanities. Chichester et al. 2015/2016." href="#schreibman_compainion_2016">Schreibman
1729 et&nbsp;al. 2015</a>.
1730 </div>
1731 </li><br><li class="footnote">
1732 <div class="footnote2" id="fn22" href="#fna22">[<a href="#fna22">22</a>]
1733 </div>
1734 <div class="footnote3"><a title="Edward Vanhoutte: The gates of hell: History and definition of digital|humanities|computing. In: Defining Digital Humanities. A Reader. Ed. by Meliss Terras / Julianne Hyhan / Edward Vanhoutte. Farnham 2013, pp. 119–156." href="#vanhoutte_gates_2013">Vanhoutte
1735 2013</a>, p. 142; <a title="Matthew&nbsp;Lee Jockers / Ted Underwood: Text-mining the humanities. In: A New Companion to Digital Humanities. Ed. by Susan Schreibman / Ray Siemens / John Unsworth. Pondicherry 2016, pp. 291–306." href="#jockers_humanities_2016">Jockers / Underwood 2016</a>, pp.
1736 292f.
1737 </div>
1738 </li><br><li class="footnote">
1739 <div class="footnote2" id="fn23" href="#fna23">[<a href="#fna23">23</a>]
1293 </div> 1740 </div>
1297 </li><br><li class="footnote"> 1744 </li><br><li class="footnote">
1298 <div class="footnote2" id="fn22" href="#fna22">[<a href="#fna22">22</a>]
1299 </div>
1300 <div class="footnote3"><a title="Charles Darwin: The expression of emotion in animals and man. London 1872." href="#darwin_expression_1872">Darwin 1872</a>, passim.
1301 </div>
1302 </li><br><li class="footnote">
1303 <div class="footnote2" id="fn23" href="#fna23">[<a href="#fna23">23</a>]
1304 </div>
1305 <div class="footnote3"><a title="Maria Gendron / Lisa Feldman&nbsp;Barrett: Reconstructing the past: A century of ideas about emotion in psychology. In: Emotion review 1 (2009), i. 4, pp. 316–339." href="#gendrin_past_2009">Gendron / Feldman&nbsp;Barrett 2009</a>.
1306 </div>
1307 </li><br><li class="footnote">
1308 <div class="footnote2" id="fn24" href="#fna24">[<a href="#fna24">24</a>] 1745 <div class="footnote2" id="fn24" href="#fna24">[<a href="#fna24">24</a>]
1309 </div> 1746 </div>
1310 <div class="footnote3"><a title="Silvan Tomkins: Affect imagery consciousness. 4 vol. New York, NY et al. 1962. Vol. I: The positive affects." href="#tomkins_consciousness_1962">Tomkins 1962</a>, passim. 1747 <div class="footnote3"><a title="Charles Darwin: The expression of emotion in animals and man. London 1872." href="#darwin_expression_1872">Darwin 1872</a>.
1311 </div> 1748 </div>
1314 </div> 1751 </div>
1315 <div class="footnote3"><a title="Paul Ekman / Richard E. Sorenson / Wallace&nbsp;V. Friesen: Pan-cultural elements in facial displays of emotion. In: Science 164 (1969), i. 3875, pp. 8688." href="#ekman_elements_1969">Ekman et&nbsp;al. 1969</a>, pp. 86-88. 1752 <div class="footnote3"><a title="Maria Gendron / Lisa Feldman&nbsp;Barrett: Reconstructing the past: A century of ideas about emotion in psychology. In: Emotion review 1 (2009), i. 4, pp. 316339." href="#gendrin_past_2009">Gendron / Feldman Barrett 2009</a>.
1316 </div> 1753 </div>
1319 </div> 1756 </div>
1757 <div class="footnote3"><a title="Silvan Tomkins: Affect imagery consciousness. 4 vol. New York, NY et al. 1962. Vol. I: The positive affects." href="#tomkins_consciousness_1962">Tomkins 1962</a>.
1758 </div>
1759 </li><br><li class="footnote">
1760 <div class="footnote2" id="fn27" href="#fna27">[<a href="#fna27">27</a>]
1761 </div>
1762 <div class="footnote3"><a title="Paul Ekman / Richard E. Sorenson / Wallace&nbsp;V. Friesen: Pan-cultural elements in facial displays of emotion. In: Science 164 (1969), i. 3875, pp. 86–88." href="#ekman_elements_1969">Ekman et al. 1969</a>,
1763 pp. 86–88.
1764 </div>
1765 </li><br><li class="footnote">
1766 <div class="footnote2" id="fn28" href="#fna28">[<a href="#fna28">28</a>]
1767 </div>
1320 <div class="footnote3"><a title="Paul Ekman: Facial expression and emotion. In: American psychologist 48 (1993), i. 4, pp. 384–392." href="#ekman_expression_1993">Ekman 1993</a>, p. 386. 1768 <div class="footnote3"><a title="Paul Ekman: Facial expression and emotion. In: American psychologist 48 (1993), i. 4, pp. 384–392." href="#ekman_expression_1993">Ekman 1993</a>, p. 386.
1322 </li><br><li class="footnote"> 1770 </li><br><li class="footnote">
1323 <div class="footnote2" id="fn27" href="#fna27">[<a href="#fna27">27</a>]
1324 </div>
1325 <div class="footnote3"><a title="Lisa&nbsp;Feldman Barrett: Discrete emotions or dimensions? The role of valence focus and arousal focus. In: Cognition &amp; Emotion 12 (1998), i. 4, pp. 579–599." href="#feldman_emotions_1998">Feldman Barrett 1998</a>, pp. 580f.
1326 </div>
1327 </li><br><li class="footnote">
1328 <div class="footnote2" id="fn28" href="#fna28">[<a href="#fna28">28</a>]
1329 </div>
1330 <div class="footnote3"><a title="James&nbsp;A. Russell: Is there universal recognition of emotion from facial expression? A review of the cross-cultural studies. In: Psychological bulletin 115 (1994), i. 1, pp. 102–141." href="#russel_recognition_1994">Russell 1994</a>;
1331 <a title="James&nbsp;A. Russell / Jo-Anne Bachorowski / José-Miguel Fernández-Dols: Facial and vocal expressions of emotion. In: Annual review of psychology 54 (2003), i. 1, pp. 329–349." href="#russel_expressions_2003">Russell et&nbsp;al. 2003</a>;
1332 <a title="Maria Gendron / Debi Roberso / Jacoba&nbsp;Marietta van&nbsp;der Vyver / Lisa&nbsp;Feldman Barrett: Perceptions of emotion from facial expressions are not culturally universal: Evidence from a remote culture. In: Emotion 14 (2014), i. 2, pp. 251–262." href="#gendron_emotion_2014">Gendron et&nbsp;al. 2014</a>;
1333 <a title="Lisa&nbsp;Feldman Barrett: How emotions are made: The secret life of the brain. Boston et al. 2017." href="#feldman_emotions_2017">Feldman Barrett 2017</a>.
1334 </div>
1335 </li><br><li class="footnote">
1336 <div class="footnote2" id="fn29" href="#fna29">[<a href="#fna29">29</a>] 1771 <div class="footnote2" id="fn29" href="#fna29">[<a href="#fna29">29</a>]
1337 </div> 1772 </div>
1338 <div class="footnote3"><a title="Robert Plutchik: The Emotions. Revided edition. Lanham et al. 1991." href="#plutchik_emotions_1991">Plutchik 1991</a>, passim. 1773 <div class="footnote3"><a title="James&nbsp;A. Russell: Is there universal recognition of emotion from facial expression? A review of the cross-cultural studies. In: Psychological bulletin 115 (1994), i. 1, pp. 102–141." href="#russell_recognition_1994">Russell
1339 </div> 1774 1994</a>; <a title="James&nbsp;A. Russell / Jo-Anne Bachorowski / José-Miguel Fernández-Dols: Facial and vocal expressions of emotion. In: Annual review of psychology 54 (2003), i. 1, pp. 329–349." href="#russell_expressions_2003">Russell et al. 2003</a>; <a title="Maria Gendron / Debi Roberso / Jacoba&nbsp;Marietta van&nbsp;der Vyver / Lisa&nbsp;Feldman Barrett: Perceptions of emotion from facial expressions are not culturally universal: Evidence from a remote culture. In: Emotion 14 (2014), i. 2, pp. 251–262." href="#gendron_emotion_2014">Gendron et al. 2014</a>; <a title="Lisa&nbsp;Feldman Barrett: How emotions are made: The secret life of the brain. Boston et al. 2017." href="#feldman_emotions_2017">Feldman Barrett
1775 2017.</a></div>
1340 </li><br><li class="footnote"> 1776 </li><br><li class="footnote">
1342 </div> 1778 </div>
1343 <div class="footnote3"><a title="Erik Cambria / Andrew Livingstone / Amir Hussain: The hourglass of emotions. In: Cognitive behavioural systems. Ed. by Anna Esposito et al. (COST 2102, Dresden, 21.-26.02.2011) Berlin 2012, pp. 144–157." href="#cambria_hourglass_2012">Cambria et&nbsp;al. 2012</a>; 1779 <div class="footnote3"><a title="Robert Plutchik: The Emotions. Revided edition. Lanham et al. 1991." href="#plutchik_emotions_1991">Plutchik 1991</a>.
1344 <a title="Suin Kim / JinYeong Bak / Alice&nbsp;Haeyun Oh: Do you feel what I feel? Social aspects of emotions in twitter conversations. In: Proceedings of the Sixth International AAAI Conference on Weblogs and Social Media. (ICWSM: 6, Dublin 04.-07.12.2012) Palo Alto, CA 2012, pp. 495–498." href="#kim_aspects_2012">Kim et&nbsp;al. 2012</a>; <a title="Jared Suttles / Nancy Ide: Distant supervision for emotion classification with discrete binary values. In: Computational Linguistics and Intelligent Text Processing. Ed. by Alexander Gelbukh. 2 volumes. (CICLing: 14, Samos, 24.-30.03.2013) Berlin et al. 2013. Vol. 2, pp. 121–136." href="#suttles_supervision_2013">Suttles / Ide 2013</a>;
1345 <a title="Damian Borth / Rongrong Ji / Tao Chen / Thomas Breuel / Shih-Fu Chang: Large-scale visual sentiment ontology and detectors using adjective noun pairs. In: Proceedings of the 21st ACM International Conference on Multimedia. (MM '13: 21, Barcelona, 21.-25.10.2013) New York, NY 2013, pp. 223–232." href="#borth_ontology_2013">Borth et&nbsp;al. 2013</a>; <a title="Muhammad Abdul-Mageed / Lyle Ungar: EmoNet: Fine-grained emotion detection with gated recurrent neural networks. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. (ACL: 55, Vancouver, 30.07.-04.08.2017) New York, NY 2017, i 1, pp. 718–728. DOI: 10.18653/v1/P17-1067" href="#abdul_emotion_2017">Abdul-Mageed /
1346 Ungar 2017</a>.
1347 </div> 1780 </div>
1350 </div> 1783 </div>
1351 <div class="footnote3"><a title="Herman Smith / Andreas Schneider: Critiquing models of emotions. In: Sociological Methods &amp; Research 37 (2009), i. 4, pp. 560–589." href="#smith_models_2009">Smith / Schneider 2009</a>, passim. 1784 <div class="footnote3"><a title="Erik Cambria / Andrew Livingstone / Amir Hussain: The hourglass of emotions. In: Cognitive behavioural systems. Ed. by Anna Esposito et al. (COST 2102, Dresden, 21.–26.02.2011) Berlin 2012, pp. 144–157." href="#cambria_hourglass_2012">Cambria et al.
1785 2012</a>; <a title="Suin Kim / JinYeong Bak / Alice&nbsp;Haeyun Oh: Do you feel what I feel? Social aspects of emotions in twitter conversations. In: Proceedings of the Sixth International AAAI Conference on Weblogs and Social Media. (ICWSM: 6, Dublin 04.-07.12.2012) Palo Alto, CA 2012, pp. 495–498." href="#kim_aspects_2012">Kim
1786 et al. 2012</a>; <a title="Jared Suttles / Nancy Ide: Distant supervision for emotion classification with discrete binary values. In: Computational Linguistics and Intelligent Text Processing. Ed. by Alexander Gelbukh. 2 volumes. (CICLing: 14, Samos, 24.–30.03.2013) Berlin et al. 2013. Vol. 2, pp. 121–136." href="#suttles_supervision_2013">Suttles / Ide 2013</a>; <a title="Damian Borth / Rongrong Ji / Tao Chen / Thomas Breuel / Shih-Fu Chang: Large-scale visual sentiment ontology and detectors using adjective noun pairs. In: Proceedings of the 21st ACM International Conference on Multimedia. (MM '13: 21, Barcelona, 21.–25.10.2013) New York, NY 2013, pp. 223–232." href="#borth_ontology_2013">Borth et al.
1787 2013</a>; <a title="Muhammad Abdul-Mageed / Lyle Ungar: EmoNet: Fine-grained emotion detection with gated recurrent neural networks. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. (ACL: 55, Vancouver, 30.07.–04.08.2017) New York, NY 2017, i 1, pp. 718–728. DOI: 10.18653/v1/P17-1067" href="#abdul_emotion_2017">Abdul-Mageed / Ungar 2017</a>.
1352 </div> 1788 </div>
1355 </div> 1791 </div>
1356 <div class="footnote3"><a title="Marsha&nbsp;L. Richins: Measuring emotions in the consumption experience. In: Journal of consumer research 24 (1997), i. 2, pp. 127–146." href="#richins_emotions_1997">Richins 1997</a>, p. 128. 1792 <div class="footnote3"><a title="Herman Smith / Andreas Schneider: Critiquing models of emotions. In: Sociological Methods &amp; Research 37 (2009), i. 4, pp. 560–589." href="#smith_models_2009">Smith / Schneider
1793 2009</a>.
1357 </div> 1794 </div>
1360 </div> 1797 </div>
1361 <div class="footnote3"><a title="James&nbsp;A. Russell: A circumplex model of affect. In: Journal of Personality and Social Psychology 39 (1980), pp. 1161–1178." href="#russel_model_1980">Russell 1980</a>. 1798 <div class="footnote3"><a title="Marsha&nbsp;L. Richins: Measuring emotions in the consumption experience. In: Journal of consumer research 24 (1997), i. 2, pp. 127–146." href="#richins_emotions_1997">Richins 1997</a>,
1799 p. 128.
1362 </div> 1800 </div>
1365 </div> 1803 </div>
1366 <div class="footnote3"><a title="Margaret&nbsp;M. Bradley / Peter&nbsp;J. Lang: Measuring emotion: the self-assessment manikin and the semantic differential. In: Journal of behavior therapy and experimental psychiatry 25 (1994), i. 1, pp. 4959." href="#bradley_emotion_1994">Bradley / Lang 1994</a>, p. 50. 1804 <div class="footnote3"><a title="James&nbsp;A. Russell: A circumplex model of affect. In: Journal of Personality and Social Psychology 39 (1980), pp. 11611178." href="#russell_model_1980">Russell 1980</a>.
1367 </div> 1805 </div>
1370 </div> 1808 </div>
1371 <div class="footnote3"><a title="James&nbsp;A. Russell: Core affect and the psychological construction of emotion. In: Psychological review 110 (2003), i. 1, pp. 145–172." href="#russel_affect_2003">Russell 2003</a>, p. 154. 1809 <div class="footnote3"><a title="Margaret&nbsp;M. Bradley / Peter&nbsp;J. Lang: Measuring emotion: the self-assessment manikin and the semantic differential. In: Journal of behavior therapy and experimental psychiatry 25 (1994), i. 1, pp. 49–59." href="#bradley_emotion_1994">Bradley / Lang
1810 1994</a>, p. 50.
1372 </div> 1811 </div>
1375 </div> 1814 </div>
1376 <div class="footnote3"><a title="Randy&nbsp;J. Larsen / Edward Diener: Promises and problems with the circumplex model of emotion. In: Emotion. Ed. by Margaret S. Clark. (= Review of personality and social psychology, 13) Newbury Park et al. 1992, pp. 2529." href="#larsen_promises_1992">Larsen / Diener 1992</a>, p. 25. 1815 <div class="footnote3"><a title="James&nbsp;A. Russell: Core affect and the psychological construction of emotion. In: Psychological review 110 (2003), i. 1, pp. 145172." href="#russell_affect_2003">Russell 2003</a>, p. 154.
1377 </div> 1816 </div>
1380 </div> 1819 </div>
1381 <div class="footnote3"><a title="James&nbsp;A. Russell / Lisa&nbsp;Feldman Barrett: Core affect, prototypical emotional episodes, and other things called emotion: dissecting the elephant. In: Journal of Personality and Social Psychology 76 (1999), i. 5, pp. 805–819." href="#russel_affect_1999">Russell / Feldman Barrett 1999</a>, p. 807. 1820 <div class="footnote3"><a title="Randy&nbsp;J. Larsen / Edward Diener: Promises and problems with the circumplex model of emotion. In: Emotion. Ed. by Margaret S. Clark. (= Review of personality and social psychology, 13) Newbury Park et al. 1992, pp. 25–29." href="#larsen_promises_1992">Larsen / Diener
1821 1992</a>, p.
1822 25.
1382 </div> 1823 </div>
1385 </div> 1826 </div>
1386 <div class="footnote3"><a title="Lars Sætre / Patrizia Lombardo / Julien Zanetta (2014b): Text and Emotions. In: Exploring Text and Emotions. Ed. by Lars Sætre / Patrizia Lombardo / Julien Zanetta. Aarhus 2014, pp. 926." href="#saetre_text_2014">Sætre 1827 <div class="footnote3"><a title="James&nbsp;A. Russell / Lisa&nbsp;Feldman Barrett: Core affect, prototypical emotional episodes, and other things called emotion: dissecting the elephant. In: Journal of Personality and Social Psychology 76 (1999), i. 5, pp. 805819." href="#russell_affect_1999">Russell / Feldman
1387 et&nbsp;al. 2014b</a>, passim. 1828 Barrett 1999</a>, p. 807.
1388 </div> 1829 </div>
1391 </div> 1832 </div>
1392 <div class="footnote3"><a title="Jacques&nbsp;M. van Meel: Representing emotions in literature and paintings: a comparative analysis. In: Poetics 23 (1995), i. 1–2, pp. 159176." href="#meel_emotions_1995">Van Meel 1995</a>, passim. 1833 <div class="footnote3"><a title="Iris B. Mauss / Michael D. Robinson: Measures of emotion: A review. In: Cognition and Emotion 23 (2009), pp. 209237. DOI: 10.1080/02699930802204677" href="#mauss_measures_2009">Mauss / Robinson 2009</a>.
1393 </div> 1834 </div>
1396 </div> 1837 </div>
1397 <div class="footnote3"><a title="Päivi Kuivalainen: Emotions in narrative: A linguistic study of Katherine Mansfield’s short fiction. In: The Electronic Journal of the Department of English at the University of Helsinki 5 (2009). [online]" href="#kuivalainen_emotions_2009">Kuivalainen 2009</a>, passim. 1838 <div class="footnote3"><a title="Klaus&nbsp;R. Scherer: What are emotions? And how can they be measured? In: Social Science Information 44 (2005), i. 4, pp. 695–729." href="#scherer_emotions_2005">Scherer 2005</a>.
1398 </div> 1839 </div>
1401 </div> 1842 </div>
1402 <div class="footnote3"><a title="James Barton: Interpreting character emotions for literature comprehension. In: Journal of Adolescent &amp; Adult Literacy 40 (1996), i. 1, pp. 2228." href="#barton_character_1996">Barton 1996</a>, passim. 1843 <div class="footnote3"><a title="Craig. A. Smith / Phoebe C. Ellsworth: Patterns of cognitive appraisal in emotion. Journal of Personality and Social Psychology 48 (1985), pp. 813838." href="#smith_patterns_1985">Smith / Ellsworth 1985</a>.
1403 </div> 1844 </div>
1406 </div> 1847 </div>
1407 <div class="footnote3"><a title="Leigh Van&nbsp;Horn: The characters within us: Readers connect with characters to create meaning and understanding. In: Journal of Adolescent &amp; Adult Literacy 40 (1997), i. 5, pp. 342–347." href="#vanhorn_characters_1997">Van&nbsp;Horn 1848 <div class="footnote3"><a title="Lars Sætre / Patrizia Lombardo / Julien Zanetta (2014b): Text and Emotions. In: Exploring Text and Emotions. Ed. by Lars Sætre / Patrizia Lombardo / Julien Zanetta. Aarhus 2014, pp. 9–26." href="#saetre_text_2014">Sætre et&nbsp;al. 2014b</a>.
1408 1997</a>, passim.
1409 </div> 1849 </div>
1412 </div> 1852 </div>
1413 <div class="footnote3"><a title="Philip&nbsp;Nicholas Johnson-Laird / Keith Oatley: The language of emotions: An analysis of a semantic field. In: Cognition and emotion 3 (1989), i. 2, pp. 81123." href="#johnson_language_1989">Johnson-Laird / Oatley 1989</a>, passim. 1853 <div class="footnote3"><a title="Jacques&nbsp;M. van Meel: Representing emotions in literature and paintings: a comparative analysis. In: Poetics 23 (1995), i. 1–2, pp. 159176." href="#meel_emotions_1995">Van Meel 1995</a>.
1414 </div> 1854 </div>
1417 </div> 1857 </div>
1418 <div class="footnote3"><a title="Hillis J.&nbsp;Miller: Text; Action; Space; Emotion in Conrad’s Nostromo. In: Exploring Text and Emotions. Ed. by Lars Saetre / Lombardo / Julien Zanetta. Aarhus 2014, pp. 91–117." href="#miller_text_2014">Miller 2014</a>, p. 92. 1858 <div class="footnote3"><a title="Päivi Kuivalainen: Emotions in narrative: A linguistic study of Katherine Mansfield’s short fiction. In: The Electronic Journal of the Department of English at the University of Helsinki 5 (2009). [online]" href="#kuivalainen_emotions_2009">Kuivalainen
1859 2009</a>.
1419 </div> 1860 </div>
1422 </div> 1863 </div>
1423 <div class="footnote3"><a title="Exploring Text and Emotions. Ed. by Lars Sætre / Patrizia Lombardo / Julien Zanetta (2014a). Aarhus 2014." href="#saetre_exploring_2014">Sætre et&nbsp;al. 2014a</a>, p. 91ff. 1864 <div class="footnote3"><a title="James Barton: Interpreting character emotions for literature comprehension. In: Journal of Adolescent &amp; Adult Literacy 40 (1996), i. 1, pp. 22–28." href="#barton_character_1996">Barton 1996</a>.
1424 </div> 1865 </div>
1427 </div> 1868 </div>
1428 <div class="footnote3"><a title="Hillis J.&nbsp;Miller: Text; Action; Space; Emotion in Conrad’s Nostromo. In: Exploring Text and Emotions. Ed. by Lars Saetre / Lombardo / Julien Zanetta. Aarhus 2014, pp. 91–117." href="#miller_text_2014">Miller 2014</a>, p. 1869 <div class="footnote3"><a title="Leigh Van&nbsp;Horn: The characters within us: Readers connect with characters to create meaning and understanding. In: Journal of Adolescent &amp; Adult Literacy 40 (1997), i. 5, pp. 342–347." href="#vanhorn_characters_1997">Van&nbsp;Horn 1997</a>.
1429 93.
1430 </div> 1870 </div>
1433 </div> 1873 </div>
1434 <div class="footnote3"><a title="Hillis J.&nbsp;Miller: Text; Action; Space; Emotion in Conrad’s Nostromo. In: Exploring Text and Emotions. Ed. by Lars Saetre / Lombardo / Julien Zanetta. Aarhus 2014, pp. 91–117." href="#miller_text_2014">Miller 2014</a>, p. 115. 1874 <div class="footnote3"><a title="Philip&nbsp;Nicholas Johnson-Laird / Keith Oatley: The language of emotions: An analysis of a semantic field. In: Cognition and emotion 3 (1989), i. 2, pp. 81–123." href="#johnson_language_1989">Johnson-Laird / Oatley
1875 1989</a>.
1435 </div> 1876 </div>
1438 </div> 1879 </div>
1880 <div class="footnote3"><a title="Joseph Hillis&nbsp;Miller: Text; Action; Space; Emotion in Conrad’s Nostromo. In: Exploring Text and Emotions. Ed. by Lars Saetre / Lombardo / Julien Zanetta. Aarhus 2014, pp. 91–117." href="#miller_text_2014">Miller 2014</a>, p. 92.
1881 </div>
1882 </li><br><li class="footnote">
1883 <div class="footnote2" id="fn49" href="#fna49">[<a href="#fna49">49</a>]
1884 </div>
1885 <div class="footnote3"><a title="Exploring Text and Emotions. Ed. by Lars Sætre / Patrizia Lombardo / Julien Zanetta (2014a). Aarhus 2014." href="#saetre_exploring_2014">Sætre et&nbsp;al.
1886 2014a</a>, pp. 91ff.
1887 </div>
1888 </li><br><li class="footnote">
1889 <div class="footnote2" id="fn50" href="#fna50">[<a href="#fna50">50</a>]
1890 </div>
1891 <div class="footnote3"><a title="Joseph Hillis&nbsp;Miller: Text; Action; Space; Emotion in Conrad’s Nostromo. In: Exploring Text and Emotions. Ed. by Lars Saetre / Lombardo / Julien Zanetta. Aarhus 2014, pp. 91–117." href="#miller_text_2014">Miller 2014</a>, p. 93.
1892 </div>
1893 </li><br><li class="footnote">
1894 <div class="footnote2" id="fn51" href="#fna51">[<a href="#fna51">51</a>]
1895 </div>
1896 <div class="footnote3"><a title="Joseph Hillis&nbsp;Miller: Text; Action; Space; Emotion in Conrad’s Nostromo. In: Exploring Text and Emotions. Ed. by Lars Saetre / Lombardo / Julien Zanetta. Aarhus 2014, pp. 91–117." href="#miller_text_2014">Miller 2014</a>, p. 115.
1897 </div>
1898 </li><br><li class="footnote">
1899 <div class="footnote2" id="fn52" href="#fna52">[<a href="#fna52">52</a>]
1900 </div>
1901 <div class="footnote3"> We recommend the essay by Katja Mellmann for further
1902 details on that topic. <a title="Katja Mellmann: E-Motion: Being Moved by Fiction and Media? Notes on Fictional Worlds, Virtual Contacts and the Reality of Emotions. In: PsyArt (2002). Article from 29.10.2002. [online]" href="#mellmann_emotion_2002">Mellmann 2002</a>.
1903 </div>
1904 </li><br><li class="footnote">
1905 <div class="footnote2" id="fn53" href="#fna53">[<a href="#fna53">53</a>]
1906 </div>
1439 <div class="footnote3"><a title="Bing Liu: Sentiment Analysis: mining opinions, sentiments, and emotions. New York, NY 2015." href="#liu_opinions_2015">Liu 2015</a>, p. 47. 1907 <div class="footnote3"><a title="Bing Liu: Sentiment Analysis: mining opinions, sentiments, and emotions. New York, NY 2015." href="#liu_opinions_2015">Liu 2015</a>, p. 47.
1441 </li><br><li class="footnote"> 1909 </li><br><li class="footnote">
1442 <div class="footnote2" id="fn49" href="#fna49">[<a href="#fna49">49</a>]
1443 </div>
1444 <div class="footnote3"><a title="Linda Barros / Pilar Rodriguez / Alvaro Ortigosa: Automatic classification of literature pieces by emotion detection: a study on quevedo’s poetry. In: 2013 Humaine Association Conference on Affective Computing and Intelligent Interaction. (ACII 2013: 5, Geneva, 02.-05.09.2013), Piscataway, NJ 2013, pp. 141–146." href="#barros_classification_2013">Barros et&nbsp;al. 2013</a>, passim.
1445 </div>
1446 </li><br><li class="footnote">
1447 <div class="footnote2" id="fn50" href="#fna50">[<a href="#fna50">50</a>]
1448 </div>
1449 <div class="footnote3"><a title="Ethan Reed: Measured unrest in the poetry of the black arts movement. Digital Humanities 2018: Puentes-Bridges. Book of Abstracts. Hg. von Jonathan Girón Palau / Isabel Galina Russell. (DH 2018, Mexico City, 26.-29.06.2018) Mexico City 2018, pp. 477–478. PDF. [online]" href="#reed_poetry_2018">Reed 2018</a>, passim.
1450 </div>
1451 </li><br><li class="footnote">
1452 <div class="footnote2" id="fn51" href="#fna51">[<a href="#fna51">51</a>]
1453 </div>
1454 <div class="footnote3"><a title="Bei Yu: An evaluation of text classification methods for literary study. In: Literary and Linguistic Computing 23 (2008), i. 3, pp. 327–343. DOI: 10.1093/llc/fqn015" href="#yu_evaluation_2008">Yu 2008</a>, passim.
1455 </div>
1456 </li><br><li class="footnote">
1457 <div class="footnote2" id="fn52" href="#fna52">[<a href="#fna52">52</a>]
1458 </div>
1459 <div class="footnote3"><a title="Albin Zehe / Martin Becker / Lena Hettinger / Andreas Hotho / Isabella Reger / Fotis Jannidis: Prediction of happy endings in German novels based on sentiment information. In: Proceedings of the Workshop on Interactions between Data Mining and Natural Language Processing 2016. Ed. by Peggy Cellier / Thierry Charnois / Andreas Hotho / Stan Matwin / Marie-Francine Moens&nbsp;/ Yannick Toussaint. (DMNLP: 3, Riva del Garda, 19.-23.09.2016) Aachen 2016, pp.&nbsp;9–16. URN: urn:nbn:de:0074-1646-4" href="#zehe_prediction_2016">Zehe et&nbsp;al. 2016</a>, passim.
1460 </div>
1461 </li><br><li class="footnote">
1462 <div class="footnote2" id="fn53" href="#fna53">[<a href="#fna53">53</a>]
1463 </div>
1464 <div class="footnote3"><a title="Saif&nbsp;M. Mohammad / Peter&nbsp;D. Turney: Crowdsourcing a word–emotion association lexicon. In: Computational Intelligence 29 (2013), i. 3, pp. 436–465." href="#mohammad_crowdsourcing_2013">Mohammad / Turney 2013</a>, passim.
1465 </div>
1466 </li><br><li class="footnote">
1467 <div class="footnote2" id="fn54" href="#fna54">[<a href="#fna54">54</a>] 1910 <div class="footnote2" id="fn54" href="#fna54">[<a href="#fna54">54</a>]
1468 </div> 1911 </div>
1912 <div class="footnote3"><a title="Linda Barros / Pilar Rodriguez / Alvaro Ortigosa: Automatic classification of literature pieces by emotion detection: a study on quevedo’s poetry. In: 2013 Humaine Association Conference on Affective Computing and Intelligent Interaction. (ACII 2013: 5, Geneva, 02.-05.09.2013), Piscataway, NJ 2013, pp. 141–146." href="#barros_classification_2013">Barros
1913 et&nbsp;al. 2013</a>.
1914 </div>
1915 </li><br><li class="footnote">
1916 <div class="footnote2" id="fn55" href="#fna55">[<a href="#fna55">55</a>]
1917 </div>
1918 <div class="footnote3"><a title="Ethan Reed: Measured unrest in the poetry of the black arts movement. Digital Humanities 2018: Puentes-Bridges. Book of Abstracts. Hg. von Jonathan Girón Palau / Isabel Galina Russell. (DH 2018, Mexico City, 26.–29.06.2018) Mexico City 2018, pp. 477–478. PDF. [online]" href="#reed_poetry_2018">Reed 2018</a></div>
1919 </li><br><li class="footnote">
1920 <div class="footnote2" id="fn56" href="#fna56">[<a href="#fna56">56</a>]
1921 </div>
1922 <div class="footnote3"><a title="Bei Yu: An evaluation of text classification methods for literary study. In: Literary and Linguistic Computing 23 (2008), i. 3, pp. 327–343. DOI: 10.1093/llc/fqn015" href="#yu_evaluation_2008">Yu 2008</a>.
1923 </div>
1924 </li><br><li class="footnote">
1925 <div class="footnote2" id="fn57" href="#fna57">[<a href="#fna57">57</a>]
1926 </div>
1927 <div class="footnote3"><a title="Ekaterina P. Volkova / Betty Mohler / Detmar Meurers / Dale Gerdemann / Heinrich H. Bülthoff: Emotional perception of fairy tales: achieving agreement in emotion annota-tion of text. In Proceedings of the NAACL HLT 2010 Workshop on Computational Ap-proaches to Analysis and Generation of Emotion in Text (2010), pp. 98–106. [online]" href="#volkova_perception_2010">Volkova et al. 2010</a>.
1928 </div>
1929 </li><br><li class="footnote">
1930 <div class="footnote2" id="fn58" href="#fna58">[<a href="#fna58">58</a>]
1931 </div>
1932 <div class="footnote3"><a title="Vikas Ganjigunte Ashok / Song Feng / Yejin Choi: Success with Style: Using Writing Style to Predict the Success of Novels. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. Ed. by Association for Computational Linguistics. (EMNLP, Seattle, WA, 18.–21.10.2013) Stroudsburg, PA 2013, pp. 1753–1764. [online]" href="#ashok_success_2013">Ashok et al. 2013?</a>.
1933 </div>
1934 </li><br><li class="footnote">
1935 <div class="footnote2" id="fn59" href="#fna59">[<a href="#fna59">59</a>]
1936 </div>
1937 <div class="footnote3"><a title="Albin Zehe / Martin Becker / Lena Hettinger / Andreas Hotho / Isabella Reger / Fotis Jannidis: Prediction of happy endings in German novels based on sentiment information. In: Proceedings of the Workshop on Interactions between Data Mining and Natural Language Processing 2016. Ed. by Peggy Cellier / Thierry Charnois / Andreas Hotho / Stan Matwin / Marie-Francine Moens&nbsp;/ Yannick Toussaint. (DMNLP: 3, Riva del Garda, 19.–23.09.2016) Aachen 2016, pp.&nbsp;9–16. URN: urn:nbn:de:0074-1646-4" href="#zehe_prediction_2016">Zehe et&nbsp;al.
1938 2016</a>.
1939 </div>
1940 </li><br><li class="footnote">
1941 <div class="footnote2" id="fn60" href="#fna60">[<a href="#fna60">60</a>]
1942 </div>
1943 <div class="footnote3"><a title="Saif&nbsp;M. Mohammad / Peter&nbsp;D. Turney: Crowdsourcing a word–emotion association lexicon. In: Computational Intelligence 29 (2013), i. 3, pp. 436–465." href="#mohammad_crowdsourcing_2013">Mohammad /
1944 Turney 2013</a>.
1945 </div>
1946 </li><br><li class="footnote">
1947 <div class="footnote2" id="fn61" href="#fna61">[<a href="#fna61">61</a>]
1948 </div>
1469 <div class="footnote3"><a title="Andrew&nbsp;J. Reagan / Lewis Mitchell / Dilan Kiley / Christopher&nbsp;M. Danforth / Peter&nbsp;Sheridan Dodds: The emotional arcs of stories are dominated by six basic shapes. In: EPJ Data Science 5 (2016), i. 1, pp. 31–43. DOI: 10.1140/epjds/s13688-016-0093-1" href="#reagan_arcs_2016">Reagan et&nbsp;al. 1949 <div class="footnote3"><a title="Andrew&nbsp;J. Reagan / Lewis Mitchell / Dilan Kiley / Christopher&nbsp;M. Danforth / Peter&nbsp;Sheridan Dodds: The emotional arcs of stories are dominated by six basic shapes. In: EPJ Data Science 5 (2016), i. 1, pp. 31–43. DOI: 10.1140/epjds/s13688-016-0093-1" href="#reagan_arcs_2016">Reagan et&nbsp;al.
1470 2016</a>, passim. 1950 2016</a>.
1471 </div>
1472 </li><br><li class="footnote">
1473 <div class="footnote2" id="fn55" href="#fna55">[<a href="#fna55">55</a>]
1474 </div>
1475 <div class="footnote3"><a title="Kurt Vonnegut: Kurt Vonnegut at the Blackboard. Ed. by Seven Stories Press. New York, NY 2005. In: Lapham’s Quarterly (2010). Article from 26.03.2010. [online]" href="#vonnegut_blackboard_2010">Vonnegut 2010 (2005)</a>, passim.
1476 </div>
1477 </li><br><li class="footnote">
1478 <div class="footnote2" id="fn56" href="#fna56">[<a href="#fna56">56</a>]
1479 </div>
1480 <div class="footnote3"><a title="Project Gutenberg. Ed. by Project Gutenberg Literary Archive Foundation. In: gutenberg.org. Salt Lake City, UT 1971-. [online]" href="#project_gutenberg_2019">Project Gutenberg 1971-2019</a>.
1481 </div>
1482 </li><br><li class="footnote">
1483 <div class="footnote2" id="fn57" href="#fna57">[<a href="#fna57">57</a>]
1484 </div>
1485 <div class="footnote3"><a title="Spyridon Samothrakis / Maria Fasli: Emotional sentence annotation helps predict fiction genre. In: PLOS ONE 10 (2015), i. 11, p. e0141922. Article from 02.11.2015. DOI: 10.1371/journal.pone.0141922" href="#samothrakis_annotation_2015">Samothrakis / Fasli 2015</a>;
1486 <a title="Evgeny Kim / Sebastian Padó / Roman Klinger (2017a): Investigating the relationship between literary genres and emotional plot development. In: Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature - proceedings of the workshop. (SIGHUM, Vancouver, 04.08.2017) Stroudsburg, PA 2017, pp. 17–26. DOI: 10.18653/v1/W17-2203" href="#kim_relationship_2017">Kim et&nbsp;al.
1487 2017a</a>; <a title="Evgeny Kim / Sebastian Padó / Roman Klinger (2017b): Prototypical emotion developments in adventures, romances, and mystery stories. In: Digital Humanities 2017: Conference Abstracts. Ed. by Rhian Lewis / Cecily Raynor / Dominic Forest / Michael Sinatra / Stéfan Sinclair. (DH 2017, Montreal, 08.-11.08.2017) Montreal 2017, pp. 288–291. PDF. [online]" href="#kim_emotion_2017">Kim et&nbsp;al. 2017b</a>.
1488 </div>
1489 </li><br><li class="footnote">
1490 <div class="footnote2" id="fn58" href="#fna58">[<a href="#fna58">58</a>]
1491 </div>
1492 <div class="footnote3"><a title="Carlo Strapparava / Alessandro Valitutti. WordNet-Affect: An affective extension of WordNet. In: Proceedings of the 4th International Conference on Language Resources and Evaluation. Ed. by Maria Teresa Lino / Maria Francisca Xavier / Fátima Ferreira / Rute Costa / Raquel Silva. 9 volumes. (LREC: 4, Lisbon, 24.-30.05.2004) Paris et al. 2004. Vol. 4, pp. 1083–1086. PDF. [online]" href="#strapparava_extension_2004">Strapparava / Valitutti 2004</a>.
1493 </div>
1494 </li><br><li class="footnote">
1495 <div class="footnote2" id="fn59" href="#fna59">[<a href="#fna59">59</a>]
1496 </div>
1497 <div class="footnote3"><a title="Evgeny Kim / Sebastian Padó / Roman Klinger (2017a): Investigating the relationship between literary genres and emotional plot development. In: Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature - proceedings of the workshop. (SIGHUM, Vancouver, 04.08.2017) Stroudsburg, PA 2017, pp. 17–26. DOI: 10.18653/v1/W17-2203" href="#kim_relationship_2017">Kim et&nbsp;al. 2017a</a>, passim.
1498 </div>
1499 </li><br><li class="footnote">
1500 <div class="footnote2" id="fn60" href="#fna60">[<a href="#fna60">60</a>]
1501 </div>
1502 <div class="footnote3"><a title="Winthrop Nelson Francis / Henry Kucera: Brown corpus manual. Preface to revised Edition. Providence, RI 1979. [online]" href="#francis_corpus_1979">Francis / Kucera 1979</a>, passim.
1503
1504 </div>
1505 </li><br><li class="footnote">
1506 <div class="footnote2" id="fn61" href="#fna61">[<a href="#fna61">61</a>]
1507 </div>
1508 <div class="footnote3"><a title="Ulrike Edith&nbsp;Gerda Henny-Krahmer: Exploration of sentiments and genre in Spanish American novels. In: Digital Humanities 2018: Puentes-Bridges. Book of Abstracts. Hg. von Jonathan Girón Palau / Isabel Galina Russell. (DH 2018, Mexico City, 26.-29.06.2018) Mexico City 2018, pp. 399–403. PDF. [online]" href="#henny_exploration_2018">Henny-Krahmer 2018</a>, passim.
1509 </div> 1951 </div>
1512 </div> 1954 </div>
1513 <div class="footnote3"><a title="Stefano Baccianella / Andrea Esuli / Fabrizio Sebastiani: Sentiwordnet 3.0: An enhanced lexical resource for sentiment analysis and opinion mining. In: Proceedings of the 7th International Conference on Language Resources and Evaluation. (LREC’10: 7, Valetta, 17.05.-23.05.2010) Paris 2010, pp. 2200–2204. PDF. [online]" href="#baccianella_resource_2010">Baccianella et&nbsp;al. 2010</a>. 1955 <div class="footnote3"><a title="Kurt Vonnegut: Kurt Vonnegut at the Blackboard. Ed. by Seven Stories Press. New York, NY 2005. In: Lapham’s Quarterly (2010). Article from 26.03.2010. [online]" href="#vonnegut_blackboard_2010">Vonnegut 2010
1514 1956 (2005)</a>.
1515 </div> 1957 </div>
1518 </div> 1960 </div>
1519 <div class="footnote3"><a title="Saif&nbsp;M. Mohammad / Peter&nbsp;D. Turney: Crowdsourcing a word–emotion association lexicon. In: Computational Intelligence 29 (2013), i. 3, pp. 436–465." href="#mohammad_crowdsourcing_2013">Mohammad / Turney 2013</a>. 1961 <div class="footnote3"><a title="Project Gutenberg. Ed. by Project Gutenberg Literary Archive Foundation. In: gutenberg.org. Salt Lake City, UT 1971–. https://www.gutenberg.org. [Webseite aus Deutschland nicht mehr erreichbar]" href="#project_gutenberg_2019">Project
1962 Gutenberg 1971–2019</a> [<i>Webseite aus Deutschland nicht mehr erreichbar</i>].
1520 </div> 1963 </div>
1523 </div> 1966 </div>
1524 <div class="footnote3"><a title="Ryan Heuser / Franco Moretti / Erik Steiner: The emotions of London. Stanford 2016. (= Literary Lab Pamphlets, 13) PDF.[online]" href="#heuser_emotions_216">Heuser et&nbsp;al. 2016</a>, passim. 1967 <div class="footnote3"><a title="Spyridon Samothrakis / Maria Fasli: Emotional sentence annotation helps predict fiction genre. In: PLOS ONE 10 (2015), i. 11, p. e0141922. Article from 02.11.2015. DOI: 10.1371/journal.pone.0141922" href="#samothrakis_annotation_2015">Samothrakis / Fasli 2015</a>; <a title="Evgeny Kim / Sebastian Padó / Roman Klinger (2017a): Investigating the relationship between literary genres and emotional plot development. In: Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature – proceedings of the workshop. (SIGHUM, Vancouver, 04.08.2017) Stroudsburg, PA 2017, pp. 17–26. DOI: 10.18653/v1/W17-2203" href="#kim_relationship_2017">Kim et&nbsp;al. 2017a</a>; <a title="Evgeny Kim / Sebastian Padó / Roman Klinger (2017b): Prototypical emotion developments in adventures, romances, and mystery stories. In: Digital Humanities 2017: Conference Abstracts. Ed. by Rhian Lewis / Cecily Raynor / Dominic Forest / Michael Sinatra / Stéfan Sinclair. (DH 2017, Montreal, 08.–11.08.2017) Montreal 2017, pp. 288–291. PDF. [online]" href="#kim_emotion_2017">Kim et&nbsp;al.
1968 2017b</a>.
1525 </div> 1969 </div>
1528 </div> 1972 </div>
1529 <div class="footnote3"><a title="Mapping emotions in Victorian London. Ed. by. Historypin. In: historypin.org. New Orleans et al. 2010-2017. [online]" href="#historypin_map_2017">Historypin 2010-2017</a>. 1973 <div class="footnote3"><a title="Carlo Strapparava / Alessandro Valitutti. WordNet-Affect: An affective extension of WordNet. In: Proceedings of the 4th International Conference on Language Resources and Evaluation. Ed. by Maria Teresa Lino / Maria Francisca Xavier / Fátima Ferreira / Rute Costa / Raquel Silva. 9 volumes. (LREC: 4, Lisbon, 24.–30.05.2004) Paris et al. 2004. Vol. 4, pp. 1083–1086. PDF. [online]" href="#strapparava_extension_2004">Strapparava
1974 / Valitutti 2004</a>.
1530 </div> 1975 </div>
1533 </div> 1978 </div>
1534 <div class="footnote3"><a title="André Bruggmann / Sara&nbsp;Irina Fabrikant: Spatializing a digital text archive about history. In: Workshop on Geographic Information Observatories 2014 : proceedings. Ed. by Krzysztof Janowicz / Benjamin Adams / Grant McKenzie / Tomi Kauppinen. (GIO 2014 / GIScience: 8, Vienna, 23.09.2014) Aachen 2014, pp. 6–14. (CEUR Workshop Proceedings, 1273) PDF. [online]" href="#bruggmann_text_2014">Bruggmann / Fabrikant 2014</a>, passim. 1979 <div class="footnote3"><a title="Evgeny Kim / Sebastian Padó / Roman Klinger (2017a): Investigating the relationship between literary genres and emotional plot development. In: Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature – proceedings of the workshop. (SIGHUM, Vancouver, 04.08.2017) Stroudsburg, PA 2017, pp. 17–26. DOI: 10.18653/v1/W17-2203" href="#kim_relationship_2017">Kim et&nbsp;al.
1980 2017a</a>.
1535 </div> 1981 </div>
1538 </div> 1984 </div>
1539 <div class="footnote3"><a title="Philip&nbsp;J. Stone / Dexter&nbsp;C. Dunphy / Marshall&nbsp;S. Smith: The General Inquirer: A computer approach to content analysis. In: American Journal of Sociology 73 (1968), i. 5, pp. 634–635." href="#stone_inquirer_19688">Stone et&nbsp;al. 1968</a>. 1985 <div class="footnote3"><a title="Winthrop Nelson Francis / Henry Kucera: Brown corpus manual. Preface to revised Edition. Providence, RI 1979. [online]" href="#francis_corpus_1979">Francis / Kucera
1986 1979</a>.
1540 </div> 1987 </div>
1543 </div> 1990 </div>
1544 <div class="footnote3"><a title="Maite Taboada / Mary&nbsp;Ann Gillies / Paul McFetridge: Sentiment classification techniques for tracking literary reputation. In: LREC workshop: Towards computational models of literary analysis. (LREC: 5, Genoa, 22.-28.05.2006) , pp. 36–43. Paris 2006. [online]" href="#taboada_classification_2006">Taboada et&nbsp;al. 2006</a>, passim; <a title="Maite Taboada / Mary&nbsp;Ann Gillies / Paul McFetridge / Robert Outtrim: Tracking literary reputation with text analysis tools. In: Meeting of the Society for Digital Humanities. Vancouver 2008. PDF. [online]" href="#taboada_reputation_2008">Taboada et&nbsp;al. 2008</a>, passim. 1991 <div class="footnote3"><a title="Ulrike Edith&nbsp;Gerda Henny-Krahmer: Exploration of sentiments and genre in Spanish American novels. In: Digital Humanities 2018: Puentes-Bridges. Book of Abstracts. Hg. von Jonathan Girón Palau / Isabel Galina Russell. (DH 2018, Mexico City, 26.–29.06.2018) Mexico City 2018, pp. 399–403. PDF. [online]" href="#henny_exploration_2018">Henny-Krahmer
1992 2018</a>.
1545 </div> 1993 </div>
1548 </div> 1996 </div>
1549 <div class="footnote3"><a title="Annie&nbsp;T. Chen / Ayoung Yoon / Ryan Shaw: People, places and emotions: Visually representing historical context in oral testimonies. In: Proceedings of the Third Workshop on Computational Models of Narrative. (CMN’12: 3, Istanbul, 26.-27.05.2012), pp. 26–27. Cambridge, MA 2012. PDF. [online]" href="#chen_people_2012">Chen et&nbsp;al. 2012</a>, passim. 1997 <div class="footnote3"><a title="Stefano Baccianella / Andrea Esuli / Fabrizio Sebastiani: Sentiwordnet 3.0: An enhanced lexical resource for sentiment analysis and opinion mining. In: Proceedings of the 7th International Conference on Language Resources and Evaluation. (LREC’10: 7, Valetta, 17.05.–23.05.2010) Paris 2010, pp. 2200–2204. PDF. [online]" href="#baccianella_resource_2010">Baccianella
1998 et&nbsp;al. 2010</a>.
1550 </div> 1999 </div>
1553 </div> 2002 </div>
1554 <div class="footnote3"><a title="Carlo Strapparava / Alessandro Valitutti. WordNet-Affect: An affective extension of WordNet. In: Proceedings of the 4th International Conference on Language Resources and Evaluation. Ed. by Maria Teresa Lino / Maria Francisca Xavier / Fátima Ferreira / Rute Costa / Raquel Silva. 9 volumes. (LREC: 4, Lisbon, 24.-30.05.2004) Paris et al. 2004. Vol. 4, pp. 1083–1086. PDF. [online]" href="#strapparava_extension_2004"> 2003 <div class="footnote3"><a title="Saif&nbsp;M. Mohammad / Peter&nbsp;D. Turney: Crowdsourcing a word–emotion association lexicon. In: Computational Intelligence 29 (2013), i. 3, pp. 436–465." href="#mohammad_crowdsourcing_2013">Mohammad /
2004 Turney 2013</a>.
2005 </div>
2006 </li><br><li class="footnote">
2007 <div class="footnote2" id="fn71" href="#fna71">[<a href="#fna71">71</a>]
2008 </div>
2009 <div class="footnote3"><a title="Ryan Heuser / Franco Moretti / Erik Steiner: The emotions of London. Stanford 2016. (= Literary Lab Pamphlets, 13) PDF.[online]" href="#heuser_emotions_216">Heuser et&nbsp;al.
2010 2016</a>.
2011 </div>
2012 </li><br><li class="footnote">
2013 <div class="footnote2" id="fn72" href="#fna72">[<a href="#fna72">72</a>]
2014 </div>
2015 <div class="footnote3"><a title="Mapping emotions in Victorian London. Ed. by Historypin. In: historypin.org. New Orleans et al. 2010–2017. [online]" href="#historypin_map_2017">Historypin
2016 2010–2017</a>.
2017 </div>
2018 </li><br><li class="footnote">
2019 <div class="footnote2" id="fn73" href="#fna73">[<a href="#fna73">73</a>]
2020 </div>
2021 <div class="footnote3"><a title="André Bruggmann / Sara&nbsp;Irina Fabrikant: Spatializing a digital text archive about history. In: Workshop on Geographic Information Observatories 2014 : proceedings. Ed. by Krzysztof Janowicz / Benjamin Adams / Grant McKenzie / Tomi Kauppinen. (GIO 2014 / GIScience: 8, Vienna, 23.09.2014) Aachen 2014, pp. 6–14. (CEUR Workshop Proceedings, 1273) PDF. [online]" href="#bruggmann_text_2014">Bruggmann /
2022 Fabrikant 2014</a>.
2023 </div>
2024 </li><br><li class="footnote">
2025 <div class="footnote2" id="fn74" href="#fna74">[<a href="#fna74">74</a>]
2026 </div>
2027 <div class="footnote3"><a title="Philip&nbsp;J. Stone / Dexter&nbsp;C. Dunphy / Marshall&nbsp;S. Smith: The General Inquirer: A computer approach to content analysis. In: American Journal of Sociology 73 (1968), i. 5, pp. 634–635." href="#stone_inquirer_19688">Stone et&nbsp;al.
2028 1968</a>.
2029 </div>
2030 </li><br><li class="footnote">
2031 <div class="footnote2" id="fn75" href="#fna75">[<a href="#fna75">75</a>]
2032 </div>
2033 <div class="footnote3"><a title="Maite Taboada / Mary&nbsp;Ann Gillies / Paul McFetridge: Sentiment classification techniques for tracking literary reputation. In: LREC workshop: Towards computational models of literary analysis. (LREC: 5, Genoa, 22.-28.05.2006) , pp. 36–43. Paris 2006. [online]" href="#taboada_classification_2006">Taboada
2034 et&nbsp;al. 2006</a>; <a title="Maite Taboada / Mary&nbsp;Ann Gillies / Paul McFetridge / Robert Outtrim: Tracking literary reputation with text analysis tools. In: Meeting of the Society for Digital Humanities. Vancouver 2008. PDF. [online]" href="#taboada_reputation_2008">Taboada et&nbsp;al. 2008</a>.
2035 </div>
2036 </li><br><li class="footnote">
2037 <div class="footnote2" id="fn76" href="#fna76">[<a href="#fna76">76</a>]
2038 </div>
2039 <div class="footnote3"><a title="Annie&nbsp;T. Chen / Ayoung Yoon / Ryan Shaw: People, places and emotions: Visually representing historical context in oral testimonies. In: Proceedings of the Third Workshop on Computational Models of Narrative. (CMN’12: 3, Istanbul, 26.–27.05.2012), pp. 26–27. Cambridge, MA 2012. PDF. [online]" href="#chen_people_2012">Chen et&nbsp;al.
2040 2012</a>.
2041 </div>
2042 </li><br><li class="footnote">
2043 <div class="footnote2" id="fn77" href="#fna77">[<a href="#fna77">77</a>]
2044 </div>
2045 <div class="footnote3"><a title="Carlo Strapparava / Alessandro Valitutti. WordNet-Affect: An affective extension of WordNet. In: Proceedings of the 4th International Conference on Language Resources and Evaluation. Ed. by Maria Teresa Lino / Maria Francisca Xavier / Fátima Ferreira / Rute Costa / Raquel Silva. 9 volumes. (LREC: 4, Lisbon, 24.–30.05.2004) Paris et al. 2004. Vol. 4, pp. 1083–1086. PDF. [online]" href="#strapparava_extension_2004">
1555 Strapparava / Valitutti 2004</a>. 2046 Strapparava / Valitutti 2004</a>.
1557 </li><br><li class="footnote"> 2048 </li><br><li class="footnote">
1558 <div class="footnote2" id="fn71" href="#fna71">[<a href="#fna71">71</a>]
1559 </div>
1560 <div class="footnote3"><a title="Oceanic Exchanges: Tracing Global Information Networks in Historical Newspaper Repositories, 1840-1914. Ed. by Oceanic Exchanges Project Team. Boston, MA 2017. [online]" href="#oceanic_global_2017">Oceanic Exchanges 2017</a>.
1561 </div>
1562 </li><br><li class="footnote">
1563 <div class="footnote2" id="fn72" href="#fna72">[<a href="#fna72">72</a>]
1564 </div>
1565 <div class="footnote3"><a title="Alessandro Marchetti / Rachele Sprugnoli / Sara Tonelli: Sentiment analysis for the humanities: the case of historical texts. In: Digital Humanities 2014: Conference Abstracts. (DH 2014, Lausanne 08.-12.07.2014), Lausanne 2014, pp. 254–257. PDF. [online]" href="#marchetti_analysis_2014">Marchetti et&nbsp;al. 2014</a>, passim.
1566 </div>
1567 </li><br><li class="footnote">
1568 <div class="footnote2" id="fn73" href="#fna73">[<a href="#fna73">73</a>]
1569 </div>
1570 <div class="footnote3"><a title="Rachele Sprugnoli / Sara Tonelli / Alessandro Marchetti / Giovanni Moretti: Towards sentiment analysis for historical texts. In: Digital Scholarship in the Humanities 31 (2016), i. 4, pp. 762–772. DOI: 10.1093/llc/fqv027" href="#sprugnoli_analysis_2016">Sprugnoli et&nbsp;al. 2016</a>, passim.
1571 </div>
1572 </li><br><li class="footnote">
1573 <div class="footnote2" id="fn74" href="#fna74">[<a href="#fna74">74</a>]
1574 </div>
1575 <div class="footnote3"><a title="ALCIDE (Analysis of Language and Content In a Digital Environment). Demo. Ed. by Center for Information Technology Digital Humanities, Fondazione Bruno Kessler / Italian-German Historical Institute. In: fbk.eu. Alcide Demo. Trento 2014-2015. [online]" href="#alcide_cit_2014">ALCIDE Demo 2014-2015</a>.
1576 </div>
1577 </li><br><li class="footnote">
1578 <div class="footnote2" id="fn75" href="#fna75">[<a href="#fna75">75</a>]
1579 </div>
1580 <div class="footnote3"><a title="Stefano Baccianella / Andrea Esuli / Fabrizio Sebastiani: Sentiwordnet 3.0: An enhanced lexical resource for sentiment analysis and opinion mining. In: Proceedings of the 7th International Conference on Language Resources and Evaluation. (LREC’10: 7, Valetta, 17.05.-23.05.2010) Paris 2010, pp. 2200–2204. PDF. [online]" href="#baccianella_resource_2010">Baccianella et&nbsp;al. 2010</a>, passim.
1581 </div>
1582 </li><br><li class="footnote">
1583 <div class="footnote2" id="fn76" href="#fna76">[<a href="#fna76">76</a>]
1584 </div>
1585 <div class="footnote3"><a title="Emanuele Pianta / Luisa Bentivogli / Christian Girardi: MultiWordNet: Developing an aligned multilingual database. In: Proceedings of 1st International Global WordNet Conference. (GWC: 1, Mysore, 21.-25.02.2002) Mysore 2002, pp. 293–302. [online]" href="#pianta_database_2002">Pianta et&nbsp;al. 2002</a>, passim.
1586 </div>
1587 </li><br><li class="footnote">
1588 <div class="footnote2" id="fn77" href="#fna77">[<a href="#fna77">77</a>]
1589 </div>
1590 <div class="footnote3"><a title="Sven Buechel / Johannes Hellrich / Udo Hahn: The course of emotion in three centuries of german text – a methodological framework. In: Digital Humanities 2017: Conference Abstracts. Ed. by Rhian Lewis et al. (DH 2017, Montreal, 08.-11.08.2017) Montreal 2017, pp. 176–179. [online]" href="#buechel_course_2017">Buechel et&nbsp;al. 2017</a>, passim.
1591 </div>
1592 </li><br><li class="footnote">
1593 <div class="footnote2" id="fn78" href="#fna78">[<a href="#fna78">78</a>] 2049 <div class="footnote2" id="fn78" href="#fna78">[<a href="#fna78">78</a>]
1594 </div> 2050 </div>
1595 <div class="footnote3"><a title="Sven Buechel / Johannes Hellrich / Udo Hahn: Feelings from the past – adapting affective lexicons for historical emotion analysis. In: Proceedings of the Workshop on Language Technology Resources and Tools for Digital Humanities. (LT4DH, Osaka, 11.12.2016) Stroudsburg, PA 2016, pp. 54–61. PDF. [online]" href="#buechel_feelings_2016">Buechel et&nbsp;al. 2016</a>, p. 54, p. 59. 2051 <div class="footnote3"><a title="Jianbo Gao / Matthew L. Jockers / John Laudun / Timothy Tangherlini: A multiscale theory for the dynamical evolution of sentiment in novels. In: International Conference on Behavioral, Economic and Socio-cultural Computing (BESC), 2016, pp. 1-4. DOI: 10.1109/BESC.2016.7804470" href="#gao_multiscale_2016">Geo et al. 2016</a>.
1596 </div> 2052 </div>
1599 </div> 2055 </div>
1600 <div class="footnote3"><a title="Deutsches Textarchiv. Grundlage für ein Referenzkorpus der neuhochdeutschen Sprache. Ed. by Berlin-Brandenburgischen Akademie der Wissenschaften. In: deutschestextarchiv.de. Berlin 2007-2019. [online]" href="#bbaw_dta_2019">Deutsches Textarchiv 2007-2019</a>. 2056 <div class="footnote3"><a title="Alessandro Marchetti / Rachele Sprugnoli / Sara Tonelli: Sentiment analysis for the humanities: the case of historical texts. In: Digital Humanities 2014: Conference Abstracts. (DH 2014, Lausanne 08.-12.07.2014), Lausanne 2014, pp. 254–257. PDF. [online]" href="#marchetti_analysis_2014">Marchetti
2057 et&nbsp;al. 2014</a>.
1601 </div> 2058 </div>
1604 </div> 2061 </div>
1605 <div class="footnote3"><a title="Inger Leemans / Janneke&nbsp;M. van&nbsp;der Zwaan / Isa Maks / Erika Kuijpers / Kristine Steenbergh: Mining embodied emotions: a comparative analysis of sentiment and emotion in dutch texts, 1600–1800. In: Digital Humanities Quaterly 11 (2017), i. 4. [online]" href="#leemans_emotions_2017">Leemans et&nbsp;al. 2017</a>, passim. 2062 <div class="footnote3"><a title="Rachele Sprugnoli / Sara Tonelli / Alessandro Marchetti / Giovanni Moretti: Towards sentiment analysis for historical texts. In: Digital Scholarship in the Humanities 31 (2016), i. 4, pp. 762–772. DOI: 10.1093/llc/fqv027" href="#sprugnoli_analysis_2016">Sprugnoli
2063 et&nbsp;al. 2016</a>.
1606 </div> 2064 </div>
1609 </div> 2067 </div>
1610 <div class="footnote3"><a title="James W. Pennebaker / Cindy K.&nbsp;Chung / Molly&nbsp;Ireland / Amy&nbsp;Gonzales / Roger J.&nbsp;Booth: The development and psychometric properties of LIWC2007. In: LIWC2007 Manual. liwc.net. 2007. PDF. [online]" href="#pennebaker_development_2007">Pennebaker et&nbsp;al. 2007</a>. 2068 <div class="footnote3"><a title="ALCIDE (Analysis of Language and Content In a Digital Environment). Demo. Ed. by Center for Information Technology Digital Humanities, Fondazione Bruno Kessler / Italian-German Historical Institute. In: fbk.eu. Alcide Demo. Trento 2014–2015. [online]" href="#alcide_cit_2014">ALCIDE Demo
2069 2014–2015</a>.
1611 </div> 2070 </div>
1614 </div> 2073 </div>
1615 <div class="footnote3"><a title="Randy Ingermanson / Peter Economy. Writing fiction for dummies. Hoboken, NJ 2009." href="#ingermanson_fiction_2009">Ingermanson / Economy 2009</a>, p. 2074 <div class="footnote3"><a title="Stefano Baccianella / Andrea Esuli / Fabrizio Sebastiani: Sentiwordnet 3.0: An enhanced lexical resource for sentiment analysis and opinion mining. In: Proceedings of the 7th International Conference on Language Resources and Evaluation. (LREC’10: 7, Valetta, 17.05.–23.05.2010) Paris 2010, pp. 2200–2204. PDF. [online]" href="#baccianella_resource_2010">Baccianella
1616 107. 2075 et&nbsp;al. 2010</a>.
1617 </div> 2076 </div>
1620 </div> 2079 </div>
1621 <div class="footnote3"><a title="Apoorv Agarwal / Anup Kotalwar / Owen Rambow: Automatic extraction of social networks from literary text: A case study on Alice in Wonderland. In: Proceedings of the Sixth International Joint Conference on Natural Language Processing. (IJCLP: 6, Nagoya 14.-18.10.2013) Nagoya 2013, pp. 12021208. [online]" href="#agarwal_extraction_2013">Agarwal et&nbsp;al. 2013</a>; 2080 <div class="footnote3"><a title="Emanuele Pianta / Luisa Bentivogli / Christian Girardi: MultiWordNet: Developing an aligned multilingual database. In: Proceedings of 1st International Global WordNet Conference. (GWC: 1, Mysore, 21.–25.02.2002) Mysore 2002, pp. 293302. [online]" href="#pianta_database_2002">Pianta et&nbsp;al.
1622 <a title="David&nbsp;K. Elson / Nicholas Dames / Kathleen&nbsp;R. McKeown: Extracting social networks from literary fiction. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics. (ACL: 48, Uppsala, 11.-18.07.2010) Red Hook, NY 2011, pp. 138–147. PDF. [online]" href="#elson_networks_2011">Elson et&nbsp;al. 2011</a>. 2081 2002</a>.
1623 </div> 2082 </div>
1626 </div> 2085 </div>
1627 <div class="footnote3"><a title="Eric&nbsp;T. Nalisnick / Henry&nbsp;S. Baird (2013a): Character-to-character sentiment analysis in shakespeare’s plays. In: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics. Ed. by Hinrich Schuetze /&nbsp;Pascale Fung /&nbsp;Massimo Poesio. 3 volumes. (ACL: 51, Sofia, 04.-09.08.2013) Red Hook, NY et al. 2013. Vol. 2: Short Papers, pp. 479–483. [online]" href="#nalisnick_analysis_2013">Nalisnick / Baird 2013a</a>, passim. 2086 <div class="footnote3"><a title="Sven Buechel / Johannes Hellrich / Udo Hahn: The course of emotion in three centuries of german text – a methodological framework. In: Digital Humanities 2017: Conference Abstracts. Ed. by Rhian Lewis et al. (DH 2017, Montreal, 08.–11.08.2017) Montreal 2017, pp. 176–179. [online]" href="#buechel_course_2017">Buechel et&nbsp;al.
2087 2017</a>.
1628 </div> 2088 </div>
1631 </div> 2091 </div>
1632 <div class="footnote3"><a title="Finn&nbsp;Årup&nbsp;Nielsen: AFINN Sentiment Lexicon. In: corpustext.com. 2011. [online]" href="#nielsen_lexicon_2011">Nielsen 2011</a>, passim. 2092 <div class="footnote3"><a title="Sven Buechel / Johannes Hellrich / Udo Hahn: Feelings from the past – adapting affective lexicons for historical emotion analysis. In: Proceedings of the Workshop on Language Technology Resources and Tools for Digital Humanities. (LT4DH, Osaka, 11.12.2016) Stroudsburg, PA 2016, pp. 54–61. PDF. [online]" href="#buechel_feelings_2016">Buechel et&nbsp;al.
2093 2016</a> p.
2094 54, p. 59.
1633 </div> 2095 </div>
1636 </div> 2098 </div>
1637 <div class="footnote3"><a title="Eric&nbsp;T. Nalisnick / Henry&nbsp;S. Baird (2013b): Extracting sentiment networks from shakespeare’s plays. In: 12th International Conference on Document Analysis and Recognition. (ICDAR: 12, Washington, DC, 25.-28.08.2013) Piscataway, NJ 2013, pp. 758–762." href="#nalisnick_networs_2013">Nalisnick / Baird 2013b</a>, passim. 2099 <div class="footnote3"><a title="Deutsches Textarchiv. Grundlage für ein Referenzkorpus der neuhochdeutschen Sprache. Ed. by Berlin-Brandenburgischen Akademie der Wissenschaften. In: deutschestextarchiv.de. Berlin 2007–2019. [online]" href="#bbaw_dta_2019">Deutsches Textarchiv
2100 2007–2019</a>.
1638 </div> 2101 </div>
1641 </div> 2104 </div>
1642 <div class="footnote3"><a title="Seth&nbsp;A. Marvel / Jon Kleinberg / Robert&nbsp;D. Kleinberg / Steven&nbsp;H. Strogatz: Continuous-time model of structural balance. In: Proceedings of the National Academy of Sciences 108 (2011), i. 5, pp. 1771–1776. DOI: 10.1073/pnas.1013213108" href="#marvel_model_2011">Marvel et&nbsp;al. 2011</a>. 2105 <div class="footnote3"><a title="Inger Leemans / Janneke&nbsp;M. van&nbsp;der Zwaan / Isa Maks / Erika Kuijpers / Kristine Steenbergh: Mining embodied emotions: a comparative analysis of sentiment and emotion in dutch texts, 1600–1800. In: Digital Humanities Quarterly 11 (2017), i. 4. [online]" href="#leemans_emotions_2017">Leemans et&nbsp;al.
2106 2017</a>.
1643 </div> 2107 </div>
1646 </div> 2110 </div>
1647 <div class="footnote3"><a title="Micha Elsner: Character-based kernels for novelistic plot structure. In: Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics. (EACL’12: 13, Avignon, 23.-27.04.2012) Stroudsburg, PA 2012, pp. 634–644. PDF. [online]" href="#elsner_kernels_2012">Elsner 2012</a>, passim; 2111 <div class="footnote3"><a title="James W. Pennebaker / Cindy K.&nbsp;Chung / Molly&nbsp;Ireland / Amy&nbsp;Gonzales / Roger J.&nbsp;Booth: The development and psychometric properties of LIWC2007. In: LIWC2007 Manual. liwc.net. 2007. PDF. [online]" href="#pennebaker_development_2007">Pennebaker
1648 <a title="Micha Elsner: Abstract representations of plot structure. In: Linguistic Issues in Language Technology 12 (2015), i. 5. PDF. [online]" href="#elsner_representations_2015">Elsner 2015</a>, passim. 2112 et&nbsp;al. 2007</a>.
1649 </div> 2113 </div>
1652 </div> 2116 </div>
1653 <div class="footnote3"><a title="Evgeny Kim / Roman Klinger: Who feels what and why? Annotation of a literature corpus with semantic roles of emotions. In: Proceedings of the 27th International Conference on Computational Linguistics. (COLING: 27, Santa Fe, NM, 20.-26.08.2018) Stroudsburg, PA 2018, pp. 1345–1359. PDF. [online]" href="#kim_annotation_2018">Kim / Klinger 2018</a>, passim. 2117 <div class="footnote3"><a title="Randy Ingermanson / Peter Economy. Writing fiction for dummies. Hoboken, NJ 2009." href="#ingermanson_fiction_2009">Ingermanson /
2118 Economy 2009</a>, p. 107.
1654 </div> 2119 </div>
1657 </div> 2122 </div>
1658 <div class="footnote3"><a title="REMAN - Relational Emotion Annotation for Fiction. Relational EMotion ANnotation – a corpus with 1720 fictional text exceprts from the Project Gutenberg. Ed. by Evgeny Kim / Roman Klinger, Universität Stuttgart, Institut für Maschinelle Sprachverarbeitung. In: ims.uni-stuttgart.de. Institut für Maschinelle Sprachverarbeitung. Forschung. Ressourcen Korpora. Stuttgart 2018. [online]" href="#reman_corpus_2019">REMAN - Relational Emotion Annotation for Fiction. Corpus 2018</a>. 2123 <div class="footnote3"><a title="Apoorv Agarwal / Anup Kotalwar / Owen Rambow: Automatic extraction of social networks from literary text: A case study on Alice in Wonderland. In: Proceedings of the Sixth International Joint Conference on Natural Language Processing. (IJCLP: 6, Nagoya 14.–18.10.2013) Nagoya 2013, pp. 1202–1208. [online]" href="#agarwal_extraction_2013">Agarwal et&nbsp;al.
2124 2013</a>; <a title="David&nbsp;K. Elson / Nicholas Dames / Kathleen&nbsp;R. McKeown: Extracting social networks from literary fiction. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics. (ACL: 48, Uppsala, 11.–18.07.2010) Red Hook, NY 2011, pp. 138–147. PDF. [online]" href="#elson_networks_2011">Elson
2125 et&nbsp;al. 2011</a>.
1659 </div> 2126 </div>
1662 </div> 2129 </div>
1663 <div class="footnote3"><a title="Florian Barth / Evgeny Kim / Sandra Murr / Roman Klinger: A reporting tool for relational visualization and analysis of character mentions in literature. In: DHd 2018: Kritik der digitalen Vernunft : Konferenzabstracts. Ed. by Georg Vogeler. (DHd 2018: 5, Köln, 26.02.-02.03.2018), Cologne 2018, pp. 123–127. PDF. [online]" href="#barth_tool_2018">Barth et&nbsp;al. 2018</a>, passim. 2130 <div class="footnote3"><a title="Eric&nbsp;T. Nalisnick / Henry&nbsp;S. Baird (2013a): Character-to-character sentiment analysis in shakespeare’s plays. In: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics. Ed. by Hinrich Schuetze /&nbsp;Pascale Fung /&nbsp;Massimo Poesio. 3 volumes. (ACL: 51, Sofia, 04.–09.08.2013) Red Hook, NY et al. 2013. Vol. 2: Short Papers, pp. 479–483. [online]" href="#nalisnick_analysis_2013">Nalisnick /
2131 Baird 2013a</a>.
1664 </div> 2132 </div>
1667 </div> 2135 </div>
1668 <div class="footnote3"><a title="Harshita Jhavar / Paramita Mirza: EMOFIEL: Mapping emotions of relationships in a story. In: Companion Proceedings of the The Web Conference 2018. (WWW’18, Lyon, 23.-27.04.2018) Geneva 2018, pp. 243–246. DOI: 10.1145/3184558.3186989" href="#jhavar_emotions_2018">Jhavar / Mirza 2136 <div class="footnote3"><a title="Finn&nbsp;Årup&nbsp;Nielsen: AFINN Sentiment Lexicon. In: corpustext.com. 2011. [online]" href="#nielsen_lexicon_2011">Nielsen
1669 2018</a>, passim. 2137 2011</a>.
1670 </div> 2138 </div>
1673 </div> 2141 </div>
1674 <div class="footnote3"><a title="EMoFiel: Emotion Mapping of Fictional Relationship. Ed. by Harshita Jhavar / Paramita Mirza, Max Planck Institute for Informatics. In: mpi-inf.mpg.de. EMoFiel. Saarbrücken 2018. [online]" href="#emofiel_mpg_2018">EMoFiel: Emotion Mapping of Fictional Relationship 2018</a>. 2142 <div class="footnote3"><a title="Eric&nbsp;T. Nalisnick / Henry&nbsp;S. Baird (2013b): Extracting sentiment networks from shakespeare’s plays. In: 12th International Conference on Document Analysis and Recognition. (ICDAR: 12, Washington, DC, 25.–28.08.2013) Piscataway, NJ 2013, pp. 758–762." href="#nalisnick_networks_2013">Nalisnick /
2143 Baird 2013b</a>.
1675 </div> 2144 </div>
1678 </div> 2147 </div>
1679 <div class="footnote3"><a title="Robert Plutchik: The Emotions. Revided edition. Lanham et al. 1991." href="#plutchik_emotions_1991">Plutchik 1991</a>, passim. 2148 <div class="footnote3"><a title="Seth&nbsp;A. Marvel / Jon Kleinberg / Robert&nbsp;D. Kleinberg / Steven&nbsp;H. Strogatz: Continuous-time model of structural balance. In: Proceedings of the National Academy of Sciences 108 (2011), i. 5, pp. 1771–1776. DOI: 10.1073/pnas.1013213108" href="#marvel_model_2011">Marvel et&nbsp;al.
2149 2011</a>.
1680 </div> 2150 </div>
1683 </div> 2153 </div>
1684 <div class="footnote3"><a title="James&nbsp;A. Russell: A circumplex model of affect. In: Journal of Personality and Social Psychology 39 (1980), pp. 1161–1178." href="#russel_model_1980">Russell 1980</a>, passim. 2154 <div class="footnote3"><a title="" href="#elsner_kernels_2012">Elsner 2012</a>;
2155 <a title="Micha Elsner: Abstract representations of plot structure. In: Linguistic Issues in Language Technology 12 (2015), i. 5. PDF. [online]" href="#elsner_representations_2015">Elsner 2015</a>.
1685 </div> 2156 </div>
1688 </div> 2159 </div>
1689 <div class="footnote3"><a title="Mattia Egloff / Antonio Lieto / Davide Picca: An ontological model for inferring psychological profiles and narrative roles of characters. In: Digital Humanities 2018: Puentes-Bridges. Book of Abstracts. Hg. von Jonathan Girón Palau / Isabel Galina Russell. (DH 2018, Mexico City, 26.-29.06.2018) Mexico City 2018, pp. 649–650. PDF. [online]" href="#egloff_model_2018">Egloff et&nbsp;al. 2018</a>, passim. 2160 <div class="footnote3"><a title="Evgeny Kim / Roman Klinger: Who feels what and why? Annotation of a literature corpus with semantic roles of emotions. In: Proceedings of the 27th International Conference on Computational Linguistics. (COLING: 27, Santa Fe, NM, 20.–26.08.2018) Stroudsburg, PA 2018, pp. 1345–1359. PDF. [online]" href="#kim_annotation_2018">Kim / Klinger
2161 2018</a>.
1690 </div> 2162 </div>
1693 </div> 2165 </div>
1694 <div class="footnote3"><a title="Viviana Patti / Federico Bertola / Antonio Lieto: Arsemotica for arsmeteo.org: Emotion-driven exploration of online art collections. In: The Twenty-Eighth International Florida Artificial Intelligence Research Society Conference. Ed. by Ingrid Russell / William Eberle. (FLAIRS: 28, Hollywood, 18.-28.05.2015) Palo Alto, CA, pp. 288–293." href="#patti_explration_2015">Patti et&nbsp;al. 2015</a>. 2166 <div class="footnote3"><a title="REMAN - Relational Emotion Annotation for Fiction. Relational EMotion ANnotation – a corpus with 1720 fictional text exceprts from the Project Gutenberg. Ed. by Evgeny Kim / Roman Klinger, Universität Stuttgart, Institut für Maschinelle Sprachverarbeitung. In: ims.uni-stuttgart.de. Institut für Maschinelle Sprachverarbeitung. Forschung. Ressourcen Korpora. Stuttgart 2018. [online]" href="#reman_corpus_2019">REMAN – Relational
2167 Emotion Annotation for Fiction. Corpus 2018</a>.
1695 </div> 2168 </div>
1698 </div> 2171 </div>
1699 <div class="footnote3"><a title="Erik Cambria / Andrew Livingstone / Amir Hussain: The hourglass of emotions. In: Cognitive behavioural systems. Ed. by Anna Esposito et al. (COST 2102, Dresden, 21.-26.02.2011) Berlin 2012, pp. 144–157." href="#cambria_hourglass_2012">Cambria et&nbsp;al. 2012</a>, passim. 2172 <div class="footnote3"><a title="Harshita Jhavar / Paramita Mirza: EMOFIEL: Mapping emotions of relationships in a story. In: Companion Proceedings of the The Web Conference 2018. (WWW’18, Lyon, 23.–27.04.2018) Geneva 2018, pp. 243–246. DOI: 10.1145/3184558.3186989" href="#jhavar_emotions_2018">Jhavar / Mirza
2173 2018</a>.
1700 </div> 2174 </div>
1703 </div> 2177 </div>
1704 <div class="footnote3"><a title="Evgeny Kim / Roman Klinger (2019b): Frowning Frodo, wincing Leia, and a seriously great friendship: Learning to classify emotional relationships of fictional characters. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Volume 1, Long and Short Papers. (NAACL-HLT, Minneapolis, MN, 02.-07.06.2019) Stroudsburg, PA 2019, pp. 647–653. DOI: 10.18653/v1/N19-1067" href="#kim_friendship_2019">Kim / Klinger 2019b</a>, passim. 2178 <div class="footnote3"><a title="EMoFiel: Emotion Mapping of Fictional Relationship. Ed. by Harshita Jhavar / Paramita Mirza, Max Planck Institute for Informatics. In: mpi-inf.mpg.de. EMoFiel. Saarbrücken 2018. [online]" href="#emofiel_mpg_2018">EMoFiel: Emotion
2179 Mapping of Fictional Relationship 2018</a>.
1705 </div> 2180 </div>
1708 </div> 2183 </div>
2184 <div class="footnote3"><a title="Robert Plutchik: The Emotions. Revided edition. Lanham et al. 1991." href="#plutchik_emotions_1991">Plutchik
2185 1991</a>.
2186 </div>
2187 </li><br><li class="footnote">
2188 <div class="footnote2" id="fn101" href="#fna101">[<a href="#fna101">101</a>]
2189 </div>
2190 <div class="footnote3"><a title="James&nbsp;A. Russell: A circumplex model of affect. In: Journal of Personality and Social Psychology 39 (1980), pp. 1161–1178." href="#russell_model_1980">Russell 1980</a>.
2191 </div>
2192 </li><br><li class="footnote">
2193 <div class="footnote2" id="fn102" href="#fna102">[<a href="#fna102">102</a>]
2194 </div>
2195 <div class="footnote3"><a title="Mattia Egloff / Antonio Lieto / Davide Picca: An ontological model for inferring psychological profiles and narrative roles of characters. In: Digital Humanities 2018: Puentes-Bridges. Book of Abstracts. Hg. von Jonathan Girón Palau / Isabel Galina Russell. (DH 2018, Mexico City, 26.–29.06.2018) Mexico City 2018, pp. 649–650. PDF. [online]" href="#egloff_model_2018">Egloff et&nbsp;al.
2196 2018</a>.
2197 </div>
2198 </li><br><li class="footnote">
2199 <div class="footnote2" id="fn103" href="#fna103">[<a href="#fna103">103</a>]
2200 </div>
2201 <div class="footnote3"><a title="Viviana Patti / Federico Bertola / Antonio Lieto: Arsemotica for arsmeteo.org: Emotion-driven exploration of online art collections. In: The Twenty-Eighth International Florida Artificial Intelligence Research Society Conference. Ed. by Ingrid Russell / William Eberle. (FLAIRS: 28, Hollywood, 18.–28.05.2015) Palo Alto, CA, pp. 288–293." href="#patti_exploration_2015">Patti et&nbsp;al.
2202 2015</a>.
2203 </div>
2204 </li><br><li class="footnote">
2205 <div class="footnote2" id="fn104" href="#fna104">[<a href="#fna104">104</a>]
2206 </div>
2207 <div class="footnote3"><a title="Erik Cambria / Andrew Livingstone / Amir Hussain: The hourglass of emotions. In: Cognitive behavioural systems. Ed. by Anna Esposito et al. (COST 2102, Dresden, 21.–26.02.2011) Berlin 2012, pp. 144–157." href="#cambria_hourglass_2012">Cambria et&nbsp;al.
2208 2012</a>.
2209 </div>
2210 </li><br><li class="footnote">
2211 <div class="footnote2" id="fn105" href="#fna105">[<a href="#fna105">105</a>]
2212 </div>
2213 <div class="footnote3"><a title="Evgeny Kim / Roman Klinger (2019b): Frowning Frodo, wincing Leia, and a seriously great friendship: Learning to classify emotional relationships of fictional characters. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Volume 1, Long and Short Papers. (NAACL-HLT, Minneapolis, MN, 02.-07.06.2019) Stroudsburg, PA 2019, pp. 647–653. DOI: 10.18653/v1/N19-1067" href="#kim_friendship_2019">Kim / Klinger
2214 2019b</a>.
2215 </div>
2216 </li><br><li class="footnote">
2217 <div class="footnote2" id="fn106" href="#fna106">[<a href="#fna106">106</a>]
2218 </div>
1709 <div class="footnote3"><a title="Evgeny Kim / Roman Klinger (2019a): An analysis of emotion communication channels in fan-fiction: Towards emotional storytelling. In: Proceedings of the Second Workshop of Storytelling. Ed. by Francis Ferraro / Ting-Hao ›Kenneth‹ Huang / Stephanie M. Lukin / Margaret Mitchell. (Florence, 01.08.2019) Stroudsburg, PA 2019. DOI: 10.18653/v1/W19-3406" href="#kim_analysis_2019">Kim / Klinger 2219 <div class="footnote3"><a title="Evgeny Kim / Roman Klinger (2019a): An analysis of emotion communication channels in fan-fiction: Towards emotional storytelling. In: Proceedings of the Second Workshop of Storytelling. Ed. by Francis Ferraro / Ting-Hao ›Kenneth‹ Huang / Stephanie M. Lukin / Margaret Mitchell. (Florence, 01.08.2019) Stroudsburg, PA 2019. DOI: 10.18653/v1/W19-3406" href="#kim_analysis_2019">Kim / Klinger
1710 2019a</a>, passim. 2220 2019a</a>.
1711 </div>
1712 </li><br><li class="footnote">
1713 <div class="footnote2" id="fn101" href="#fna101">[<a href="#fna101">101</a>]
1714 </div>
1715 <div class="footnote3"> Their
1716 analysis is based on <a title="Jacques&nbsp;M. van Meel: Representing emotions in literature and paintings: a comparative analysis. In: Poetics 23 (1995), i. 1–2, pp. 159–176." href="#meel_emotions_1995">Van Meel 1995</a> we mentioned in
1717 <a title="" href="#hd7">Section 3</a>.
1718 </div>
1719 </li><br><li class="footnote">
1720 <div class="footnote2" id="fn102" href="#fna102">[<a href="#fna102">102</a>]
1721 </div>
1722 <div class="footnote3"><a title="Sergio Rinaldi / Pietro Landi / Fabio Della Rossa: Small discoveries can have great consequences in love affairs: the case of Beauty and the Beast. In: International Journal of Bifurcation and Chaos 23 (2013), i. 11." href="#rinaldi_discoveries_2013">Rinaldi et&nbsp;al. 2013</a>, passim.
1723 </div>
1724 </li><br><li class="footnote">
1725 <div class="footnote2" id="fn103" href="#fna103">[<a href="#fna103">103</a>]
1726 </div>
1727 <div class="footnote3"><a title="Mikhail Zhuravlev / Irina Golovacheva / Polina de&nbsp;Mauny: Mathematical modelling of love affairs between the characters of the pre-masochistic novel. In: 2014 Second World Conference on Complex Systems (WCCS: 2, Adagir, 10.-12.11.2014) Piscataway, NJ 2014, pp. 396–401." href="#zhuravlev_affairs_2014">Zhuravlev et&nbsp;al. 2014</a>, passim.
1728 </div>
1729 </li><br><li class="footnote">
1730 <div class="footnote2" id="fn104" href="#fna104">[<a href="#fna104">104</a>]
1731 </div>
1732 <div class="footnote3"><a title="Sajad Jafari / Julien Clinton Sprott / Seyed Mohammad Reza Hashemi Golpayegani: Layla and Majnun: A complex love story. In: Nonlinear Dynamics 83 (2016), i. 1, pp. 615–622." href="#jafri_story_2016">Jafari et&nbsp;al. 2016</a>, passim.
1733 </div>
1734 </li><br><li class="footnote">
1735 <div class="footnote2" id="fn105" href="#fna105">[<a href="#fna105">105</a>]
1736 </div>
1737 <div class="footnote3"><a title="Clifford&nbsp;W. Anderson / George&nbsp;E. McMaster: Modeling emotional tone in stories using tension levels and categorical states. In: Computers and the Humanities 20 (1986), i. 1, pp. 3–9." href="#anderson_tone_1986"> Anderson / McMaster 1986</a>, passim.
1738 </div>
1739 </li><br><li class="footnote">
1740 <div class="footnote2" id="fn106" href="#fna106">[<a href="#fna106">106</a>]
1741 </div>
1742 <div class="footnote3"><a title="David&nbsp;Reuben Jerome Heise: Semantic differential profiles for 1,000 most frequent English words. In: Psychological Monographs: General and Applied 79 (1965), i. 8, pp. 1–31." href="#heise_profiles_1965">Heise 1965</a>, passim.
1743 </div> 2221 </div>
1746 </div> 2224 </div>
1747 <div class="footnote3"><a title="Clifford&nbsp;W. Anderson / George&nbsp;E. McMaster: Computer assisted modeling of affective tone in written documents. In: Computers and the Humanities 16 (1982), i. 1, pp. 1–9." href="#anderson_computer_1982">Anderson / McMaster 1982</a>; 2225 <div class="footnote3"> Their analysis is based on <a title="Jacques&nbsp;M. van Meel: Representing emotions in literature and paintings: a comparative analysis. In: Poetics 23 (1995), i. 1–2, pp. 159–176." href="#meel_emotions_1995">Van Meel 1995</a> we mentioned in <a title="" href="#hd9">section 3</a>.
1748 <a title="Clifford&nbsp;W. Anderson / George&nbsp;E. McMaster: Emotional tone in Peter Rabbit before and after simplification. In: Empirical Studies of the Arts 11 (1993), i. 2, pp. 177–185." href="#anderson_tone_1993">Anderson / McMaster 1993</a>.
1749 </div> 2226 </div>
1752 </div> 2229 </div>
1753 <div class="footnote3"><a title="Cecilia&nbsp;Ovesdotter Alm / Richard Sproat: Emotional sequencing and development in fairy tales. In: Affective computing and intelligent interaction. First international conference. Proceedings. Ed. by Jianhua Tao et al. (ACII’05, Beijing, 22.-24.10.2005) Berlin et al. 2005, pp. 668–674." href="#alm_sequencing_2005">Alm / Sproat 2005</a>, passim. 2230 <div class="footnote3"><a title="Sergio Rinaldi / Pietro Landi / Fabio Della Rossa: Small discoveries can have great consequences in love affairs: the case of Beauty and the Beast. In: International Journal of Bifurcation and Chaos 23 (2013), i. 11." href="#rinaldi_discoveries_2013">Rinaldi
2231 et&nbsp;al. 2013</a>.
1754 </div> 2232 </div>
1757 </div> 2235 </div>
1758 <div class="footnote3"><a title="Saif M. Mohammad: From once upon a time to happily ever after: Tracking emotions in novels and fairy tales. In: Proceedings of the 5th ACL-HLT Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities. Ed. by Kalliopi Zervanou /&nbsp;Piroska Lendvai. (ACL-HT: 5, Portland, OR, 23.-24.06.2011) Stroudsburg, PA 2011, pp. 105–114. PDF. [online]" href="#mohammad_time_2011">Mohammad 2011</a>, passim; 2236 <div class="footnote3"><a title="Mikhail Zhuravlev / Irina Golovacheva / Polina de&nbsp;Mauny: Mathematical modelling of love affairs between the characters of the pre-masochistic novel. In: 2014 Second World Conference on Complex Systems (WCCS: 2, Adagir, 10.–12.11.2014) Piscataway, NJ 2014, pp. 396–401." href="#zhuravlev_affairs_2014">Zhuravlev
1759 <a title="Saif&nbsp;M. Mohammad: From once upon a time to happily ever after: Tracking emotions in mail and books. In: Decision Support Systems 53 (2012), i. 4, pp. 730–741." href="#mohammad_time_2012">Mohammad 2237 et&nbsp;al. 2014</a>.
1760 2012</a>, passim.
1761 </div> 2238 </div>
1764 </div> 2241 </div>
1765 <div class="footnote3"><a title="Roman Klinger / Surayya&nbsp;Samat Suliya / Nils Reiter: Automatic Emotion Detection for Quantitative Literary Studies – A case study based on Franz Kafka’s “Das Schloss” and “Amerika”. In: Digital Humanities 2016: Conference Abstracts. Ed. by Maciej Eder / Jan Rybicki. (DH 2016, Kraków. 11.-16.07.2016) Kraków 2016, pp. 826–828. PDF. [online]" href="#klinger_emotion_2016">Klinger et&nbsp;al. 2016</a>, passim. 2242 <div class="footnote3"><a title="Sajad Jafari / Julien Clinton Sprott / Seyed Mohammad Reza Hashemi Golpayegani: Layla and Majnun: A complex love story. In: Nonlinear Dynamics 83 (2016), i. 1, pp. 615–622." href="#jafri_story_2016">Jafari et&nbsp;al.
2243 2016</a>.
1766 </div> 2244 </div>
1769 </div> 2247 </div>
1770 <div class="footnote3"><a title="Evgeny Kim / Sebastian Padó / Roman Klinger (2017b): Prototypical emotion developments in adventures, romances, and mystery stories. In: Digital Humanities 2017: Conference Abstracts. Ed. by Rhian Lewis / Cecily Raynor / Dominic Forest / Michael Sinatra / Stéfan Sinclair. (DH 2017, Montreal, 08.-11.08.2017) Montreal 2017, pp. 288–291. PDF. [online]" href="#kim_emotion_2017">Kim et&nbsp;al. 2017b</a>, passim. 2248 <div class="footnote3"><a title="Clifford&nbsp;W. Anderson / George&nbsp;E. McMaster: Modeling emotional tone in stories using tension levels and categorical states. In: Computers and the Humanities 20 (1986), i. 1, pp. 3–9." href="#anderson_tone_1986"> Anderson /
2249 McMaster 1986</a>.
1771 </div> 2250 </div>
1774 </div> 2253 </div>
1775 <div class="footnote3"><a title="Gustav Freytag: Die Technik des Dramas. Leipzig 1863." href="#freytag_technik_1863">Freytag 1863</a>, passim. 2254 <div class="footnote3"><a title="David&nbsp;Reuben Jerome Heise: Semantic differential profiles for 1,000 most frequent English words. In: Psychological Monographs: General and Applied 79 (1965), i. 8, pp. 1–31." href="#heise_profiles_1965">Heise 1965</a>.
1776 </div> 2255 </div>
1779 </div> 2258 </div>
2259 <div class="footnote3"><a title="Clifford&nbsp;W. Anderson / George&nbsp;E. McMaster: Computer assisted modeling of affective tone in written documents. In: Computers and the Humanities 16 (1982), i. 1, pp. 1–9." href="#anderson_computer_1982">Anderson /
2260 McMaster 1982</a>; <a title="Clifford&nbsp;W. Anderson / George&nbsp;E. McMaster: Emotional tone in Peter Rabbit before and after simplification. In: Empirical Studies of the Arts 11 (1993), i. 2, pp. 177–185." href="#anderson_tone_1993">Anderson / McMaster 1993</a>.
2261 </div>
2262 </li><br><li class="footnote">
2263 <div class="footnote2" id="fn114" href="#fna114">[<a href="#fna114">114</a>]
2264 </div>
2265 <div class="footnote3"><a title="Cecilia&nbsp;Ovesdotter Alm / Richard Sproat: Emotional sequencing and development in fairy tales. In: Affective computing and intelligent interaction. First international conference. Proceedings. Ed. by Jianhua Tao et al. (ACII’05, Beijing, 22.-24.10.2005) Berlin et al. 2005, pp. 668–674." href="#alm_sequencing_2005">Alm / Sproat
2266 2005</a>.
2267 </div>
2268 </li><br><li class="footnote">
2269 <div class="footnote2" id="fn115" href="#fna115">[<a href="#fna115">115</a>]
2270 </div>
2271 <div class="footnote3"><a title="Saif M. Mohammad: From once upon a time to happily ever after: Tracking emotions in novels and fairy tales. In: Proceedings of the 5th ACL-HLT Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities. Ed. by Kalliopi Zervanou /&nbsp;Piroska Lendvai. (ACL-HT: 5, Portland, OR, 23.–24.06.2011) Stroudsburg, PA 2011, pp. 105–114. PDF. [online]" href="#mohammad_time_2011">Mohammad
2272 2011</a>; <a title="Saif&nbsp;M. Mohammad: From once upon a time to happily ever after: Tracking emotions in mail and books. In: Decision Support Systems 53 (2012), i. 4, pp. 730–741." href="#mohammad_time_2012">Mohammad 2012</a>.
2273 </div>
2274 </li><br><li class="footnote">
2275 <div class="footnote2" id="fn116" href="#fna116">[<a href="#fna116">116</a>]
2276 </div>
2277 <div class="footnote3"><a title="Roman Klinger / Surayya&nbsp;Samat Suliya / Nils Reiter: Automatic Emotion Detection for Quantitative Literary Studies – A case study based on Franz Kafka’s “Das Schloss” and “Amerika”. In: Digital Humanities 2016: Conference Abstracts. Ed. by Maciej Eder / Jan Rybicki. (DH 2016, Kraków. 11.–16.07.2016) Kraków 2016, pp. 826–828. PDF. [online]" href="#klinger_emotion_2016">Klinger et&nbsp;al.
2278 2016</a>.
2279 </div>
2280 </li><br><li class="footnote">
2281 <div class="footnote2" id="fn117" href="#fna117">[<a href="#fna117">117</a>]
2282 </div>
2283 <div class="footnote3"><a title="Thomas Schmidt / Manuel Burghardt: An Evaluation of Lexicon-based Sentiment Analysis Techniques for the Plays of Gotthold Ephraim Lessing. In: Proceedings of the Second Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature. Stroudsburg, PA 2018, pp. 139–149. [online]" href="#schmidt_evaluation_2018">Schmidt / Burghardt 2018</a>.
2284 </div>
2285 </li><br><li class="footnote">
2286 <div class="footnote2" id="fn118" href="#fna118">[<a href="#fna118">118</a>]
2287 </div>
2288 <div class="footnote3"><a title="Evgeny Kim / Sebastian Padó / Roman Klinger (2017b): Prototypical emotion developments in adventures, romances, and mystery stories. In: Digital Humanities 2017: Conference Abstracts. Ed. by Rhian Lewis / Cecily Raynor / Dominic Forest / Michael Sinatra / Stéfan Sinclair. (DH 2017, Montreal, 08.–11.08.2017) Montreal 2017, pp. 288–291. PDF. [online]" href="#kim_emotion_2017">Kim et&nbsp;al.
2289 2017b</a>.
2290 </div>
2291 </li><br><li class="footnote">
2292 <div class="footnote2" id="fn119" href="#fna119">[<a href="#fna119">119</a>]
2293 </div>
2294 <div class="footnote3"><a title="Gustav Freytag: Die Technik des Dramas. Leipzig 1863." href="#freytag_technik_1863">Freytag
2295 1863</a>.
2296 </div>
2297 </li><br><li class="footnote">
2298 <div class="footnote2" id="fn120" href="#fna120">[<a href="#fna120">120</a>]
2299 </div>
1780 <div class="footnote3"><a title="Tuomo Kakkonen / Gordana Galic&nbsp;Kakkonen: Sentiprofiler: Creating comparable visual profiles of sentimental content in texts. In: Proceedings of the Workshop on Language Technologies for Digital Humanities and Cultural Heritage. Ed. by Cristina Vertan / Milena Slavcheva / Petya Osenova / Stelios Piperidis. (DigHum / RANLP: 8, Hissar, 16.09.2011) Shoumen 2011, pp. 62–69. PDF. [online]" href="#kakkonen_profiles_2011">Kakkonen / 2300 <div class="footnote3"><a title="Tuomo Kakkonen / Gordana Galic&nbsp;Kakkonen: Sentiprofiler: Creating comparable visual profiles of sentimental content in texts. In: Proceedings of the Workshop on Language Technologies for Digital Humanities and Cultural Heritage. Ed. by Cristina Vertan / Milena Slavcheva / Petya Osenova / Stelios Piperidis. (DigHum / RANLP: 8, Hissar, 16.09.2011) Shoumen 2011, pp. 62–69. PDF. [online]" href="#kakkonen_profiles_2011">Kakkonen /
1781 Galic&nbsp;Kakkonen 2011</a>, passim. 2301 Galic&nbsp;Kakkonen 2011</a>.
1782 </div> 2302 </div>
1783 </li><br><li class="footnote"> 2303 </li><br><li class="footnote">
1784 <div class="footnote2" id="fn114" href="#fna114">[<a href="#fna114">114</a>] 2304 <div class="footnote2" id="fn121" href="#fna121">[<a href="#fna121">121</a>]
1785 </div> 2305 </div>
1786 <div class="footnote3"><a title="Corina Koolen: Women’s books versus books by women. Digital Humanities 2018: Puentes-Bridges. Book of Abstracts. Hg. von Jonathan Girón Palau / Isabel Galina Russell. (DH 2018, Mexico City, 26.-29.06.2018) Mexico City 2018, pp. 219–222. PDF. [online]" href="#koolen_books_2018">Koolen 2018</a>, passim. 2306 <div class="footnote3"><a title="Corina Koolen: Women’s books versus books by women. Digital Humanities 2018: Puentes-Bridges. Book of Abstracts. Hg. von Jonathan Girón Palau / Isabel Galina Russell. (DH 2018, Mexico City, 26.29.06.2018) Mexico City 2018, pp. 219–222. PDF. [online]" href="#koolen_books_2018">Koolen 2018</a>.
1787 </div> 2307 </div>
1788 </li><br><li class="footnote"> 2308 </li><br><li class="footnote">
1789 <div class="footnote2" id="fn115" href="#fna115">[<a href="#fna115">115</a>] 2309 <div class="footnote2" id="fn122" href="#fna122">[<a href="#fna122">122</a>]
1790 </div> 2310 </div>
1794 </li><br><li class="footnote"> 2314 </li><br><li class="footnote">
1795 <div class="footnote2" id="fn116" href="#fna116">[<a href="#fna116">116</a>]
1796 </div>
1797 <div class="footnote3"><a title="Eve Kraicer / Andrew Piper: Social characters: The hierarchy of gender in contemporary English-language fiction. In: Journal of Cultural Analytics (2019). Article from 30.01.2019. DOI: 10.22148/16.032" href="#kracier_characters_2019">Kraicer / Piper 2019</a>, passim.
1798 </div>
1799 </li><br><li class="footnote">
1800 <div class="footnote2" id="fn117" href="#fna117">[<a href="#fna117">117</a>]
1801 </div>
1802 <div class="footnote3"><a title="Bing Liu: Sentiment analysis and subjectivity. In: Handbook of natural language processing. Ed. by Nitin Indurkhya / Fred Jacob Damerau. 2. edition. Boca Raton, FL 2010, pp. 627–666." href="#liu_analysis_2010">Liu et&nbsp;al. 2010</a>, passim.
1803 </div>
1804 </li><br><li class="footnote">
1805 <div class="footnote2" id="fn118" href="#fna118">[<a href="#fna118">118</a>]
1806 </div>
1807 <div class="footnote3"><a title="Olivier Morin / Alberto Acerbi: Birth of the cool: a two-centuries decline in emotional expression in anglophone fiction. In: Cognition and Emotion 31 (2017), i. 8, pp. 1663–1675." href="#morin_birth_2017">Morin / Acerbi 2017</a>, passim.
1808 </div>
1809 </li><br><li class="footnote">
1810 <div class="footnote2" id="fn119" href="#fna119">[<a href="#fna119">119</a>]
1811 </div>
1812 <div class="footnote3"><a title="Google Books Ngram Viewer. Ed. by Google. In: http://storage.googleapis.com. Version 2. 2012. [online]" href="#google_books_2012">Google Books Ngram Viewer 2012</a>.
1813 </div>
1814 </li><br><li class="footnote">
1815 <div class="footnote2" id="fn120" href="#fna120">[<a href="#fna120">120</a>]
1816 </div>
1817 <div class="footnote3"><a title="James W. Pennebaker / Cindy K.&nbsp;Chung / Molly&nbsp;Ireland / Amy&nbsp;Gonzales / Roger J.&nbsp;Booth: The development and psychometric properties of LIWC2007. In: LIWC2007 Manual. liwc.net. 2007. PDF. [online]" href="#pennebaker_development_2007">Pennebaker et&nbsp;al. 2007</a>.
1818 </div>
1819 </li><br><li class="footnote">
1820 <div class="footnote2" id="fn121" href="#fna121">[<a href="#fna121">121</a>]
1821 </div>
1822 <div class="footnote3"><a title="Alexander R. Bentley / Alberto Acerbi / Paul Ormerod / Vasileios Lampos: Books average previous decade of economic misery. In: PLOS ONE 9 (2014), i. 1, p. e83147. Article from 08.01.2014. DOI: 10.1371/journal.pone.0083147" href="#bentley_books_2014">Bentley et&nbsp;al. 2014</a>, passim.
1823 </div>
1824 </li><br><li class="footnote">
1825 <div class="footnote2" id="fn122" href="#fna122">[<a href="#fna122">122</a>]
1826 </div>
1827 <div class="footnote3"><a title="Olivier Morin / Alberto Acerbi: Birth of the cool: a two-centuries decline in emotional expression in anglophone fiction. In: Cognition and Emotion 31 (2017), i. 8, pp. 1663–1675." href="#morin_birth_2017">Morin / Acerbi 2017</a>, passim.
1828 </div>
1829 </li><br><li class="footnote">
1830 <div class="footnote2" id="fn123" href="#fna123">[<a href="#fna123">123</a>] 2315 <div class="footnote2" id="fn123" href="#fna123">[<a href="#fna123">123</a>]
1831 </div> 2316 </div>
1832 <div class="footnote3"><a title="Mika&nbsp;V. Mäntylä / Daniel Graziotin / Miikka Kuutila: The evolution of sentiment analysis – a review of research topics, venues, and top cited papers. In: Computer Science Review 27 (2018), pp. 16–32." href="#maentylae_evolution_2018">Mäntylä et&nbsp;al. 2018</a>, passim. 2317 <div class="footnote3"><a title="Eve Kraicer / Andrew Piper: Social characters: The hierarchy of gender in contemporary English-language fiction. In: Journal of Cultural Analytics (2019). Article from 30.01.2019. DOI: 10.22148/16.032" href="#kraicer_characters_2019">Kraicer /
2318 Piper 2019</a>.
1833 </div> 2319 </div>
1836 </div> 2322 </div>
1837 <div class="footnote3"><a title="Clifford&nbsp;W. Anderson / George&nbsp;E. McMaster: Computer assisted modeling of affective tone in written documents. In: Computers and the Humanities 16 (1982), i. 1, pp. 1–9." href="#anderson_computer_1982">Anderson / McMaster 1982</a>, passim. 2323 <div class="footnote3"><a title="Bing Liu: Sentiment analysis and subjectivity. In: Handbook of natural language processing. Ed. by Nitin Indurkhya / Fred Jacob Damerau. 2. edition. Boca Raton, FL 2010, pp. 627–666." href="#liu_analysis_2010">Liu et&nbsp;al.
2324 2010</a>.
1838 </div> 2325 </div>
1841 </div> 2328 </div>
1842 <div class="footnote3"><a title="Ethan Reed: Measured unrest in the poetry of the black arts movement. Digital Humanities 2018: Puentes-Bridges. Book of Abstracts. Hg. von Jonathan Girón Palau / Isabel Galina Russell. (DH 2018, Mexico City, 26.-29.06.2018) Mexico City 2018, pp. 477–478. PDF. [online]" href="#reed_poetry_2018">Reed 2018</a>, passim. 2329 <div class="footnote3"><a title="Olivier Morin / Alberto Acerbi: Birth of the cool: a two-centuries decline in emotional expression in anglophone fiction. In: Cognition and Emotion 31 (2017), i. 8, pp. 1663–1675." href="#morin_birth_2017">Morin / Acerbi
2330 2017</a>.
1843 </div> 2331 </div>
1846 </div> 2334 </div>
1847 <div class="footnote3"><a title="Ryan Heuser / Franco Moretti / Erik Steiner: The emotions of London. Stanford 2016. (= Literary Lab Pamphlets, 13) PDF.[online]" href="#heuser_emotions_216">Heuser 2335 <div class="footnote3"><a title="Google Books Ngram Viewer. Ed. by Google. In: http://storage.googleapis.com. Version 2. 2012. [online]" href="#google_books_2012">Google Books Ngram
1848 et&nbsp;al. 2016</a>, passim. 2336 Viewer 2012</a>.
1849 </div> 2337 </div>
1852 </div> 2340 </div>
1853 <div class="footnote3"><a title="Olivier Morin / Alberto Acerbi: Birth of the cool: a two-centuries decline in emotional expression in anglophone fiction. In: Cognition and Emotion 31 (2017), i. 8, pp. 1663–1675." href="#morin_birth_2017">Morin and Acerbi 2341 <div class="footnote3"><a title="James W. Pennebaker / Cindy K.&nbsp;Chung / Molly&nbsp;Ireland / Amy&nbsp;Gonzales / Roger J.&nbsp;Booth: The development and psychometric properties of LIWC2007. In: LIWC2007 Manual. liwc.net. 2007. PDF. [online]" href="#pennebaker_development_2007">Pennebaker
1854 2017</a>, passim. 2342 et&nbsp;al. 2007</a>.
1855 </div> 2343 </div>
1858 </div> 2346 </div>
1859 <div class="footnote3"><a title="Nan&nbsp;Z. Da: The computational case against computational literary studies. In: Critical Inquiry 45 (2019), i. 3, pp. 601–639." href="#da_case_2019">Da 2347 <div class="footnote3"><a title="Alexander R. Bentley / Alberto Acerbi / Paul Ormerod / Vasileios Lampos: Books average previous decade of economic misery. In: PLOS ONE 9 (2014), i. 1, p. e83147. Article from 08.01.2014. DOI: 10.1371/journal.pone.0083147" href="#bentley_books_2014">Bentley et&nbsp;al.
1860 2019</a>, passim. 2348 2014</a>.
2349 </div>
2350 </li><br><li class="footnote">
2351 <div class="footnote2" id="fn129" href="#fna129">[<a href="#fna129">129</a>]
2352 </div>
2353 <div class="footnote3"><a title="Olivier Morin / Alberto Acerbi: Birth of the cool: a two-centuries decline in emotional expression in anglophone fiction. In: Cognition and Emotion 31 (2017), i. 8, pp. 1663–1675." href="#morin_birth_2017">Morin / Acerbi
2354 2017</a>.
2355 </div>
2356 </li><br><li class="footnote">
2357 <div class="footnote2" id="fn130" href="#fna130">[<a href="#fna130">130</a>]
2358 </div>
2359 <div class="footnote3"><a title="Mika&nbsp;V. Mäntylä / Daniel Graziotin / Miikka Kuutila: The evolution of sentiment analysis – a review of research topics, venues, and top cited papers. In: Computer Science Review 27 (2018), pp. 16–32." href="#maentylae_evolution_2018">Mäntylä et&nbsp;al.
2360 2018</a>.
2361 </div>
2362 </li><br><li class="footnote">
2363 <div class="footnote2" id="fn131" href="#fna131">[<a href="#fna131">131</a>]
2364 </div>
2365 <div class="footnote3"><a title="Clifford&nbsp;W. Anderson / George&nbsp;E. McMaster: Computer assisted modeling of affective tone in written documents. In: Computers and the Humanities 16 (1982), i. 1, pp. 1–9." href="#anderson_computer_1982">Anderson / McMaster
2366 1982</a>.
2367 </div>
2368 </li><br><li class="footnote">
2369 <div class="footnote2" id="fn132" href="#fna132">[<a href="#fna132">132</a>]
2370 </div>
2371 <div class="footnote3"><a title="Laura Ana Maria Oberländer / Kevin Reich / Roman Klinger: Experiencers, Stimuli, or Targets: Which Semantic Roles Enable Machine Learning to Infer the Emotions? In: Proceedings of the Third Workshop on Computational Modeling of People's Opinions, Personality, and Emotion's in Social Media. Barcelona 2020, pp. 119–128. [online]" href="#oberlaender_experiencers">
2372 Oberländer et al. 2020</a>.
1861 </div> 2373 </div>
1865 <div class="bibliography"> 2377 <div class="bibliography">
1866 <hr><a name="hd27"> </a><h2> 2378 <hr><a name="div31"> </a><div id="bibliography"><a name="hd29"> </a><h2>
1867 <div style="position:relative;width:90%;">Bibliographic References</div> 2379 <div style="position:relative;width:90%;">Bibliographic References</div>
1869 <ul class="bibl"> 2381 <ul class="bibl">
1870 <li class="biblio" id="abdul_emotion_2017">Muhammad Abdul-Mageed / Lyle Ungar: EmoNet: Fine-grained emotion detection with 2382 <li class="biblio" id="ashok_success_2013">Vikas Ganjigunte Ashok / Song Feng / Yejin Choi: Success with Style:
1871 gated recurrent neural networks. In: Proceedings of the 55th Annual Meeting of the 2383 Using Writing Style to Predict the Success of Novels. In: Proceedings of
1872 Association for Computational Linguistics. (ACL: 55, Vancouver, 30.07.-04.08.2017) 2384 the 2013 Conference on Empirical Methods in Natural Language Processing. Ed. by Association
1873 New York, NY 2017, i 1, pp. 718–728. DOI: <a href="http://dx.doi.org/10.18653/v1/P17-1067" target="_blank">10.18653/v1/P17-1067</a></li><br><li class="biblio" id="agarwal_extraction_2013">Apoorv Agarwal / Anup Kotalwar / Owen Rambow: Automatic extraction of social 2385 for Computational Linguistics.
1874 networks from literary text: A case study on Alice in Wonderland. In: Proceedings 2386 (EMNLP, Seattle, WA, 18.–21.10.2013) Stroudsburg, PA 2013, pp. 1753–1764.
1875 of 2387 [<a href="https://aclanthology.org/D13-1181" target="_blank">online</a>]
1876 the Sixth International Joint Conference on Natural Language Processing. (IJCLP: 6, 2388 </li><br><li class="biblio" id="abdul_emotion_2017">Muhammad Abdul-Mageed / Lyle Ungar: EmoNet:
1877 Nagoya 14.-18.10.2013) Nagoya 2013, pp. 1202–1208. [<a href="https://www.aclweb.org/anthology/I13-1171/" target="_blank">online</a>] 2389 Fine-grained emotion detection with gated recurrent neural networks. In:
1878 2390 Proceedings of the 55th Annual Meeting of the Association for Computational
1879 </li><br><li class="biblio" id="alm_sequencing_2005">Cecilia&nbsp;Ovesdotter Alm / Richard Sproat: Emotional sequencing and development in 2391 Linguistics. (ACL: 55, Vancouver, 30.07.–04.08.2017) New York, NY 2017, i 1,
1880 fairy tales. In: Affective computing and intelligent interaction. First international 2392 pp. 718–728. DOI: <a href="http://dx.doi.org/10.18653/v1/P17-1067" target="_blank">10.18653/v1/P17-1067</a></li><br><li class="biblio" id="agarwal_extraction_2013">Apoorv Agarwal / Anup Kotalwar / Owen
1881 conference. Proceedings. Ed. by Jianhua Tao et al. (ACII’05, Beijing, 2393 Rambow: Automatic extraction of social networks from literary text: A case
1882 22.-24.10.2005) Berlin et al. 2005, pp. 668–674. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=501430601" target="_blank">Nachweis im GVK</a>] 2394 study on Alice in Wonderland. In: Proceedings of the Sixth International Joint
1883 </li><br><li class="biblio" id="alcide_cit_2014">ALCIDE (Analysis of Language and Content In a Digital Environment). Demo. Ed. by Center 2395 Conference on Natural Language Processing. (IJCLP: 6, Nagoya 14.–18.10.2013)
1884 for Information Technology Digital Humanities, Fondazione Bruno Kessler / Italian-German 2396 Nagoya 2013, pp. 1202–1208. [<a href="https://www.aclweb.org/anthology/I13-1171/" target="_blank">online</a>]
1885 Historical Institute. 2397 </li><br><li class="biblio" id="alm_sequencing_2005">Cecilia&nbsp;Ovesdotter Alm / Richard Sproat:
1886 In: fbk.eu. Alcide Demo. Trento 2014-2015. [<a href="http://celct.fbk.eu:8080/Alcide_Demo/" target="_blank">online</a>] 2398 Emotional sequencing and development in fairy tales. In: Affective computing
1887 </li><br><li class="biblio" id="anderson_computer_1982">Clifford&nbsp;W. Anderson / George&nbsp;E. McMaster: Computer assisted modeling of affective 2399 and intelligent interaction. First international conference. Proceedings. Ed.
1888 tone in written documents. In: Computers and the Humanities 16 (1982), i. 1, pp. 1–9. 2400 by Jianhua Tao et al. (ACII’05, Beijing, 22.-24.10.2005) Berlin et al. 2005,
1889 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129534900" target="_blank">Nachweis im GVK</a>] 2401 pp. 668–674. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=501430601" target="_blank">Nachweis im GVK</a>]
1890 </li><br><li class="biblio" id="anderson_tone_1986">Clifford&nbsp;W. Anderson / George&nbsp;E. McMaster: Modeling emotional tone in stories 2402 </li><br><li class="biblio" id="alcide_cit_2014">ALCIDE (Analysis of Language and Content In a
1891 using tension levels and categorical states. In: Computers and the Humanities 20 2403 Digital Environment). Demo. Ed. by Center for Information Technology Digital
1892 (1986), i. 1, pp. 3–9. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129534900" target="_blank">Nachweis im GVK</a>] 2404 Humanities, Fondazione Bruno Kessler / Italian-German Historical Institute. In:
1893 </li><br><li class="biblio" id="anderson_tone_1993">Clifford&nbsp;W. Anderson / George&nbsp;E. McMaster: Emotional tone in Peter Rabbit before 2405 fbk.eu. Alcide Demo. Trento 2014–2015. [<a href="https://alcidedigitale.fbk.eu/" target="_blank">online</a>]
1894 and after simplification. In: Empirical Studies of the Arts 11 (1993), i. 2, pp. 2406 </li><br><li class="biblio" id="anderson_computer_1982">Clifford&nbsp;W. Anderson / George&nbsp;E. McMaster:
1895 177–185. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=168690268" target="_blank">Nachweis im GVK</a>] 2407 Computer assisted modeling of affective tone in written documents. In:
1896 </li><br><li class="biblio" id="aristotele_poetics_1996">Aristotle: Poetics. Penguin 1996. (= Penguin Classics)</li><br><li class="biblio" id="baccianella_resource_2010">Stefano Baccianella / Andrea Esuli / Fabrizio Sebastiani: Sentiwordnet 3.0: An 2408 Computers and the Humanities 16 (1982), i. 1, pp. 1–9. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129534900" target="_blank">Nachweis im GVK</a>]
1897 enhanced lexical resource for sentiment analysis and opinion mining. In: Proceedings 2409 </li><br><li class="biblio" id="anderson_tone_1986">Clifford&nbsp;W. Anderson / George&nbsp;E. McMaster:
1898 of the 7th International Conference on Language Resources and Evaluation. (LREC’10: 2410 Modeling emotional tone in stories using tension levels and categorical states.
1899 7, Valetta, 17.05.-23.05.2010) Paris 2010, pp. 2200–2204. PDF. [<a href="http://www.lrec-conf.org/proceedings/lrec2010/pdf/769_Paper.pdf" target="_blank">online</a>] 2411 In: Computers and the Humanities 20 (1986), i. 1, pp. 3–9. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129534900" target="_blank">Nachweis im GVK</a>]
1900 </li><br><li class="biblio" id="bal_fiction_2013">P. Matthijs Bal / Martijn Veltkamp: How does fiction reading influence empathy? An 2412 </li><br><li class="biblio" id="anderson_tone_1993">Clifford&nbsp;W. Anderson / George&nbsp;E. McMaster:
1901 experimental investigation on the role of emotional transportation. In: PLOS ONE 8 2413 Emotional tone in Peter Rabbit before and after simplification. In: Empirical
1902 (2013), i. 1, p. e55341. Article from 30.01.2013. DOI: <a href="https://doi.org/10.1371/journal.pone.0055341" target="_blank">10.1371/journal.pone.0055341</a></li><br><li class="biblio" id="feldman_emotions_1998">Lisa&nbsp;Feldman Barrett: Discrete emotions or dimensions? The role of valence focus 2414 Studies of the Arts 11 (1993), i. 2, pp. 177–185. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=168690268" target="_blank">Nachweis im GVK</a>]
1903 and arousal focus. In: Cognition &amp; Emotion 12 (1998), i. 4, pp. 579–599. 2415 </li><br><li class="biblio" id="aristotle_poetics_1996">Aristotle: Poetics. Penguin 1996. (=
1904 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=168132915" target="_blank">Nachweis im GVK</a>] 2416 Penguin Classics)
1905 </li><br><li class="biblio" id="feldman_emotions_2017">Lisa&nbsp;Feldman Barrett: How emotions are made: The secret life of the brain. Boston 2417 </li><br><li class="biblio" id="baccianella_resource_2010">Stefano Baccianella / Andrea Esuli /
1906 et al. 2017. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=878645292" target="_blank">Nachweis im GVK</a>] 2418 Fabrizio Sebastiani: Sentiwordnet 3.0: An enhanced lexical resource for
1907 </li><br><li class="biblio" id="barros_classification_2013">Linda Barros / Pilar Rodriguez / Alvaro Ortigosa: Automatic classification of 2419 sentiment analysis and opinion mining. In: Proceedings of the 7th International
1908 literature pieces by emotion detection: a study on quevedo’s poetry. In: 2013 Humaine 2420 Conference on Language Resources and Evaluation. (LREC’10: 7, Valetta,
1909 Association Conference on Affective Computing and Intelligent Interaction. (ACII 2421 17.05.–23.05.2010) Paris 2010, pp. 2200–2204. PDF. [<a href="http://www.lrec-conf.org/proceedings/lrec2010/pdf/769_Paper.pdf" target="_blank">online</a>]
1910 2013: 5, Geneva, 02.-05.09.2013), Piscataway, NJ 2013, pp. 141–146. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=782440541" target="_blank">Nachweis im GVK</a>] 2422 </li><br><li class="biblio" id="bal_fiction_2013">P. Matthijs Bal / Martijn Veltkamp: How does
1911 </li><br><li class="biblio" id="barth_tool_2018">Florian Barth / Evgeny Kim / Sandra Murr / Roman Klinger: A reporting tool for 2423 fiction reading influence empathy? An experimental investigation on the role of
1912 relational visualization and analysis of character mentions in literature. In: DHd 2424 emotional transportation. In: PLOS ONE 8 (2013), i. 1, p. e55341. Article from
1913 2018: Kritik der digitalen Vernunft : Konferenzabstracts. Ed. by Georg Vogeler. (DHd 2425 30.01.2013. DOI: <a href="https://doi.org/10.1371/journal.pone.0055341" target="_blank">10.1371/journal.pone.0055341</a></li><br><li class="biblio" id="feldman_emotions_1998">Lisa&nbsp;Feldman Barrett: Discrete emotions or
1914 2018: 5, Köln, 26.02.-02.03.2018), Cologne 2018, pp. 123–127. PDF. [<a href="http://dhd2018.uni-koeln.de/wp-content/uploads/boa-DHd2018-web-ISBN.pdf" target="_blank">online</a>] [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=1636190855" target="_blank">Nachweis im GVK</a>] 2426 dimensions? The role of valence focus and arousal focus. In: Cognition &amp;
1915 </li><br><li class="biblio" id="barton_character_1996">James Barton: Interpreting character emotions for literature comprehension. In: 2427 Emotion 12 (1998), i. 4, pp. 579–599. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=168132915" target="_blank">Nachweis im GVK</a>]
1916 Journal of Adolescent &amp; Adult Literacy 40 (1996), i. 1, pp. 22–28. 2428 </li><br><li class="biblio" id="feldman_emotions_2017">Lisa&nbsp;Feldman Barrett: How emotions are made:
1917 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=19105335X" target="_blank">Nachweis im GVK</a>] 2429 The secret life of the brain. Boston et al. 2017. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=878645292" target="_blank">Nachweis im GVK</a>]
1918 </li><br><li class="biblio" id="bentley_books_2014">Alexander R. Bentley / Alberto Acerbi / Paul Ormerod / Vasileios Lampos: Books 2430 </li><br><li class="biblio" id="barros_classification_2013">Linda Barros / Pilar Rodriguez / Alvaro
1919 average previous decade of economic misery. In: PLOS ONE 9 (2014), i. 1, p. e83147. 2431 Ortigosa: Automatic classification of literature pieces by emotion detection: a
1920 Article from 08.01.2014. DOI: <a href="https://doi.org/10.1371/journal.pone.0083147" target="_blank">10.1371/journal.pone.0083147</a></li><br><li class="biblio" id="berry_introduction_2012">David&nbsp;M. Berry: Introduction: Understanding the digital humanities. In: 2432 study on quevedo’s poetry. In: 2013 Humaine Association Conference on Affective
1921 Understanding digital humanities. Ed. by David M. Berry. Houndmills et al. 2012, pp. 2433 Computing and Intelligent Interaction. (ACII 2013: 5, Geneva, 02.-05.09.2013),
1922 1–20. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=684052288" target="_blank">Nachweis im GVK</a>] 2434 Piscataway, NJ 2013, pp. 141–146. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=782440541" target="_blank">Nachweis im GVK</a>]
1923 </li><br><li class="biblio" id="boot_translation_2017">Peter Boot / Hanna Zijlstra / Rinie Geenen: The Dutch translation of the 2435 </li><br><li class="biblio" id="barton_character_1996">James Barton: Interpreting character emotions
1924 linguistic inquiry and word count (LIWC) 2007 dictionary. In: Dutch Journal of 2436 for literature comprehension. In: Journal of Adolescent &amp; Adult Literacy 40
1925 Applied Linguistics 6 (2017), i. 1, pp. 65–76. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=688084109" target="_blank">Nachweis im GVK</a>] 2437 (1996), i. 1, pp. 22–28. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=19105335X" target="_blank">Nachweis im GVK</a>]
1926 </li><br><li class="biblio" id="borth_ontology_2013">Damian Borth / Rongrong Ji / Tao Chen / Thomas Breuel / Shih-Fu Chang: Large-scale 2438 </li><br><li class="biblio" id="bentley_books_2014">Alexander R. Bentley / Alberto Acerbi / Paul
1927 visual sentiment ontology and detectors using adjective noun pairs. In: Proceedings 2439 Ormerod / Vasileios Lampos: Books average previous decade of economic misery.
1928 of the 21st ACM International Conference on Multimedia. (MM '13: 21, Barcelona, 2440 In: PLOS ONE 9 (2014), i. 1, p. e83147. Article from 08.01.2014. DOI: <a href="https://doi.org/10.1371/journal.pone.0083147" target="_blank">10.1371/journal.pone.0083147</a></li><br><li class="biblio" id="berry_introduction_2012">David&nbsp;M. Berry: Introduction: Understanding
1929 21.-25.10.2013) New York, NY 2013, pp. 223–232. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=786496479" target="_blank">Nachweis im GVK</a>] 2441 the digital humanities. In: Understanding digital humanities. Ed. by David M.
1930 </li><br><li class="biblio" id="bradley_emotion_1994">Margaret&nbsp;M. Bradley / Peter&nbsp;J. Lang: Measuring emotion: the self-assessment 2442 Berry. Houndmills et al. 2012, pp. 1–20. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=684052288" target="_blank">Nachweis im GVK</a>]
1931 manikin and the semantic differential. In: Journal of behavior therapy and 2443 </li><br><li class="biblio" id="boot_translation_2017">Peter Boot / Hanna Zijlstra / Rinie Geenen:
1932 experimental psychiatry 25 (1994), i. 1, pp. 49–59. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129850713" target="_blank">Nachweis im GVK</a>] 2444 The Dutch translation of the linguistic inquiry and word count (LIWC) 2007
1933 </li><br><li class="biblio" id="bruggmann_text_2014">André Bruggmann / Sara&nbsp;Irina Fabrikant: Spatializing a digital text archive about 2445 dictionary. In: Dutch Journal of Applied Linguistics 6 (2017), i. 1, pp. 65–76.
1934 history. In: Workshop on Geographic Information Observatories 2014 : proceedings. 2446 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=688084109" target="_blank">Nachweis im GVK</a>]
1935 Ed. 2447 </li><br><li class="biblio" id="borth_ontology_2013">Damian Borth / Rongrong Ji / Tao Chen / Thomas
1936 by Krzysztof Janowicz / Benjamin Adams / Grant McKenzie / Tomi Kauppinen. (GIO 2014 2448 Breuel / Shih-Fu Chang: Large-scale visual sentiment ontology and detectors
1937 / 2449 using adjective noun pairs. In: Proceedings of the 21st ACM International
1938 GIScience: 8, Vienna, 23.09.2014) Aachen 2014, pp. 6–14. (CEUR Workshop Proceedings, 2450 Conference on Multimedia. (MM '13: 21, Barcelona, 21.–25.10.2013) New York, NY
1939 1273) PDF. [<a href="http://ceur-ws.org/Vol-1273/paper1.pdf" target="_blank">online</a>] 2451 2013, pp. 223–232. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=786496479" target="_blank">Nachweis im GVK</a>]
1940 </li><br><li class="biblio" id="bryant_television_1984">Jennings Bryant / Dolf Zillmann: Using television to alleviate boredom and stress: 2452 </li><br><li class="biblio" id="bradley_emotion_1994">Margaret&nbsp;M. Bradley / Peter&nbsp;J. Lang: Measuring
1941 Selective exposure as a function of induced excitational states. In: Journal of 2453 emotion: the self-assessment manikin and the semantic differential. In: Journal
1942 Broadcasting &amp; Electronic Media 28 (1984), i. 1, pp. 1–20. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=130412023" target="_blank">Nachweis im GVK</a>] 2454 of behavior therapy and experimental psychiatry 25 (1994), i. 1, pp. 49–59.
1943 </li><br><li class="biblio" id="buechel_feelings_2016">Sven Buechel / Johannes Hellrich / Udo Hahn: Feelings from the past – adapting 2455 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129850713" target="_blank">Nachweis im GVK</a>]
1944 affective lexicons for historical emotion analysis. In: Proceedings of the Workshop 2456 </li><br><li class="biblio" id="bruggmann_text_2014">André Bruggmann / Sara&nbsp;Irina Fabrikant:
1945 on Language Technology Resources and Tools for Digital Humanities. (LT4DH, Osaka, 2457 Spatializing a digital text archive about history. In: Workshop on Geographic
1946 11.12.2016) Stroudsburg, PA 2016, pp. 54–61. PDF. [<a href="https://www.aclweb.org/anthology/W16-4008.pdf" target="_blank">online</a>] 2458 Information Observatories 2014 : proceedings. Ed. by Krzysztof Janowicz /
1947 </li><br><li class="biblio" id="buechel_course_2017">Sven Buechel / Johannes Hellrich / Udo Hahn: The course of emotion in three 2459 Benjamin Adams / Grant McKenzie / Tomi Kauppinen. (GIO 2014 / GIScience: 8,
1948 centuries of german text – a methodological framework. In: Digital Humanities 2017: 2460 Vienna, 23.09.2014) Aachen 2014, pp. 6–14. (CEUR Workshop Proceedings, 1273)
1949 Conference Abstracts. Ed. by Rhian Lewis et al. (DH 2017, Montreal, 08.-11.08.2017) 2461 PDF. [<a href="http://ceur-ws.org/Vol-1273/paper1.pdf" target="_blank">online</a>]
1950 Montreal 2017, pp. 176–179. [<a href="https://dh2017.adho.org/program/abstracts/" target="_blank">online</a>] 2462 </li><br><li class="biblio" id="bryant_television_1984">Jennings Bryant / Dolf Zillmann: Using
1951 </li><br><li class="biblio" id="cambria_hourglass_2012">Erik Cambria / Andrew Livingstone / Amir Hussain: The hourglass of emotions. In: 2463 television to alleviate boredom and stress: Selective exposure as a function of
1952 Cognitive behavioural systems. Ed. by Anna Esposito et al. (COST 2102, Dresden, 2464 induced excitational states. In: Journal of Broadcasting &amp; Electronic Media
1953 21.-26.02.2011) Berlin 2012, pp. 144–157. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=727822047" target="_blank">Nachweis im GVK</a>] 2465 28 (1984), i. 1, pp. 1–20. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=130412023" target="_blank">Nachweis im GVK</a>]
1954 </li><br><li class="biblio" id="chen_people_2012">Annie&nbsp;T. Chen / Ayoung Yoon / Ryan Shaw: People, places and emotions: Visually 2466 </li><br><li class="biblio" id="buechel_feelings_2016">Sven Buechel / Johannes Hellrich / Udo Hahn:
1955 representing historical context in oral testimonies. In: Proceedings of the Third 2467 Feelings from the past – adapting affective lexicons for historical emotion
1956 Workshop on Computational Models of Narrative. (CMN’12: 3, Istanbul, 26.-27.05.2012), 2468 analysis. In: Proceedings of the Workshop on Language Technology Resources and
1957 pp. 26–27. Cambridge, MA 2012. PDF. [<a href="http://narrative.csail.mit.edu/cmn12/abstracts.pdf" target="_blank">online</a>] 2469 Tools for Digital Humanities. (LT4DH, Osaka, 11.12.2016) Stroudsburg, PA 2016,
1958 </li><br><li class="biblio" id="oceanic_global_2017">Oceanic Exchanges: Tracing Global Information Networks in Historical Newspaper 2470 pp. 54–61. PDF. [<a href="https://www.aclweb.org/anthology/W16-4008.pdf" target="_blank">online</a>]
1959 Repositories, 1840-1914. Ed. by Oceanic Exchanges Project Team. Boston, MA 2017. 2471 </li><br><li class="biblio" id="buechel_course_2017">Sven Buechel / Johannes Hellrich / Udo Hahn:
1960 [<a href="https://oceanicexchanges.org/" target="_blank">online</a>] 2472 The course of emotion in three centuries of german text – a methodological
1961 </li><br><li class="biblio" id="da_case_2019">Nan&nbsp;Z. Da: The computational case against computational literary studies. In: 2473 framework. In: Digital Humanities 2017: Conference Abstracts. Ed. by Rhian
1962 Critical Inquiry 45 (2019), i. 3, pp. 601–639. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=12956110X" target="_blank">Nachweis im GVK</a>] 2474 Lewis et al. (DH 2017, Montreal, 08.–11.08.2017) Montreal 2017, pp. 176–179.
1963 </li><br><li class="biblio" id="darwin_expression_1872">Charles Darwin: The expression of emotion in animals and man. London 1872. 2475 [<a href="https://dh2017.adho.org/program/abstracts/" target="_blank">online</a>]
1964 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=486457699" target="_blank">Nachweis im GVK</a>] 2476 </li><br><li class="biblio" id="cambria_hourglass_2012">Erik Cambria / Andrew Livingstone / Amir
1965 </li><br><li class="biblio" id="bbaw_dta_2019">Deutsches Textarchiv. Grundlage für ein Referenzkorpus der neuhochdeutschen Sprache. 2477 Hussain: The hourglass of emotions. In: Cognitive behavioural systems. Ed. by
1966 Ed. by Berlin-Brandenburgischen Akademie der Wissenschaften. 2478 Anna Esposito et al. (COST 2102, Dresden, 21.–26.02.2011) Berlin 2012, pp.
1967 In: deutschestextarchiv.de. Berlin 2007-2019. [<a href="https://deutschestextarchiv.de" target="_blank">online</a>] 2479 144–157. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=727822047" target="_blank">Nachweis im GVK</a>]
1968 </li><br><li class="biblio" id="djikic_art_2009">Maja Djikic / Keith Oatley / Sara Zoeterman / Jordan&nbsp;B. Peterson: On being moved 2480 </li><br><li class="biblio" id="chen_people_2012">Annie&nbsp;T. Chen / Ayoung Yoon / Ryan Shaw: People,
1969 by art: How reading fiction transforms the self. In: Creativity Research Journal 21 2481 places and emotions: Visually representing historical context in oral
1970 (2009), i. 1, pp. 24–29. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=186447965" target="_blank">Nachweis im GVK</a>] 2482 testimonies. In: Proceedings of the Third Workshop on Computational Models of
1971 </li><br><li class="biblio" id="djikic_minds_2013">Maja Djikic / Keith Oatley / Mihnea&nbsp;C. Moldoveanu: Reading other minds: Effects of 2483 Narrative. (CMN’12: 3, Istanbul, 26.–27.05.2012), pp. 26–27. Cambridge, MA
1972 literature on empathy. In: Scientific Study of Literature 3 (2013), i. 1, pp. 28–47. 2484 2012. PDF. [<a href="http://narrative.csail.mit.edu/cmn12/abstracts.pdf" target="_blank">online</a>]
1973 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=655139664" target="_blank">Nachweis im GVK</a>] 2485 </li><br><li class="biblio" id="oceanic_global_2017">Oceanic Exchanges: Tracing Global Information
1974 </li><br><li class="biblio" id="egloff_model_2018">Mattia Egloff / Antonio Lieto / Davide Picca: An ontological model for inferring 2486 Networks in Historical Newspaper Repositories, 1840–1914. Ed. by Oceanic
1975 psychological profiles and narrative roles of characters. In: Digital Humanities 2487 Exchanges Project Team. Boston, MA 2017. [<a href="https://oceanicexchanges.org/" target="_blank">online</a>]
1976 2018: Puentes-Bridges. Book of Abstracts. Hg. von Jonathan Girón Palau / Isabel 2488 </li><br><li class="biblio" id="da_case_2019">Nan&nbsp;Z. Da: The computational case against
1977 Galina Russell. (DH 2018, Mexico City, 26.-29.06.2018) Mexico City 2018, pp. 649–650. 2489 computational literary studies. In: Critical Inquiry 45 (2019), i. 3, pp.
1978 PDF. [<a href="https://dh2018.adho.org/wp-content/uploads/2018/06/dh2018_abstracts.pdf" target="_blank">online</a>] 2490 601–639. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=12956110X" target="_blank">Nachweis im GVK</a>]
1979 </li><br><li class="biblio" id="ekman_expression_1993">Paul Ekman: Facial expression and emotion. In: American psychologist 48 (1993), i. 2491 </li><br><li class="biblio" id="darwin_expression_1872">Charles Darwin: The expression of emotion in
1980 4, pp. 384–392. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129507261" target="_blank">Nachweis im GVK</a>] 2492 animals and man. London 1872. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=486457699" target="_blank">Nachweis im GVK</a>]
1981 </li><br><li class="biblio" id="ekman_elements_1969">Paul Ekman / Richard E. Sorenson / Wallace&nbsp;V. Friesen: Pan-cultural elements in 2493 </li><br><li class="biblio" id="bbaw_dta_2019">Deutsches Textarchiv. Grundlage für ein
1982 facial displays of emotion. In: Science 164 (1969), i. 3875, pp. 86–88. 2494 Referenzkorpus der neuhochdeutschen Sprache. Ed. by Berlin-Brandenburgischen
1983 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=12931482X" target="_blank">Nachweis im GVK</a>] 2495 Akademie der Wissenschaften. In: deutschestextarchiv.de. Berlin 2007–2019.
1984 </li><br><li class="biblio" id="elsner_kernels_2012">Micha Elsner: Character-based kernels for novelistic plot structure. In: 2496 [<a href="https://deutschestextarchiv.de" target="_blank">online</a>]
1985 Proceedings of the 13th Conference of the European Chapter of the Association for 2497 </li><br><li class="biblio" id="djikic_art_2009">Maja Djikic / Keith Oatley / Sara Zoeterman /
1986 Computational Linguistics. (EACL’12: 13, Avignon, 23.-27.04.2012) Stroudsburg, PA 2498 Jordan&nbsp;B. Peterson: On being moved by art: How reading fiction transforms the
1987 2012, pp. 634–644. PDF. [<a href="https://dl.acm.org/ft_gateway.cfm?id=2380893" target="_blank">online</a>] 2499 self. In: Creativity Research Journal 21 (2009), i. 1, pp. 24–29. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=186447965" target="_blank">Nachweis im GVK</a>]
1988 </li><br><li class="biblio" id="elsner_representations_2015">Micha Elsner: Abstract representations of plot structure. In: Linguistic Issues in 2500 </li><br><li class="biblio" id="djikic_minds_2013">Maja Djikic / Keith Oatley / Mihnea&nbsp;C.
1989 Language Technology 12 (2015), i. 5. PDF. [<a href="http://csli-lilt.stanford.edu/ojs/index.php/LiLT/article/view/57/47" target="_blank">online</a>] 2501 Moldoveanu: Reading other minds: Effects of literature on empathy. In:
1990 </li><br><li class="biblio" id="elson_networks_2011">David&nbsp;K. Elson / Nicholas Dames / Kathleen&nbsp;R. McKeown: Extracting social networks 2502 Scientific Study of Literature 3 (2013), i. 1, pp. 28–47. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=655139664" target="_blank">Nachweis im GVK</a>]
1991 from literary fiction. In: Proceedings of the 48th Annual Meeting of the Association 2503 </li><br><li class="biblio" id="egloff_model_2018">Mattia Egloff / Antonio Lieto / Davide Picca: An
1992 for Computational Linguistics. (ACL: 48, Uppsala, 11.-18.07.2010) Red Hook, NY 2011, 2504 ontological model for inferring psychological profiles and narrative roles of
1993 pp. 138–147. PDF. [<a href="https://www.aclweb.org/anthology/P10-1015.pdf" target="_blank">online</a>] [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=644235802" target="_blank">Nachweis im GVK</a>] 2505 characters. In: Digital Humanities 2018: Puentes-Bridges. Book of Abstracts.
1994 </li><br><li class="biblio" id="emofiel_mpg_2018">EMoFiel: Emotion Mapping of Fictional Relationship. Ed. by Harshita Jhavar / Paramita 2506 Hg. von Jonathan Girón Palau / Isabel Galina Russell. (DH 2018, Mexico City,
1995 Mirza, Max Planck Institute for Informatics. 2507 26.–29.06.2018) Mexico City 2018, pp. 649–650. PDF. [<a href="https://dh2018.adho.org/wp-content/uploads/2018/06/dh2018_abstracts.pdf" target="_blank">online</a>]
1996 In: mpi-inf.mpg.de. EMoFiel. Saarbrücken 2018. [<a href="https://gate.d5.mpi-inf.mpg.de/emofiel/" target="_blank">online</a>] 2508 </li><br><li class="biblio" id="ekman_expression_1993">Paul Ekman: Facial expression and emotion.
1997 </li><br><li class="biblio" id="francis_corpus_1979">Winthrop Nelson Francis / Henry Kucera: Brown corpus manual. Preface to revised 2509 In: American psychologist 48 (1993), i. 4, pp. 384–392. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129507261" target="_blank">Nachweis im GVK</a>]
1998 Edition. Providence, RI 1979. [<a href="http://clu.uni.no/icame/manuals/BROWN/INDEX.HTM" target="_blank">online</a>] 2510 </li><br><li class="biblio" id="ekman_elements_1969">Paul Ekman / Richard E. Sorenson / Wallace&nbsp;V.
1999 </li><br><li class="biblio" id="freytag_technik_1863">Gustav Freytag: Die Technik des Dramas. Leipzig 1863. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=13347772X" target="_blank">Nachweis im GVK</a>] 2511 Friesen: Pan-cultural elements in facial displays of emotion. In: Science 164
2000 </li><br><li class="biblio" id="gendrin_past_2009">Maria Gendron / Lisa Feldman&nbsp;Barrett: Reconstructing the past: A century of ideas 2512 (1969), i. 3875, pp. 86–88. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=12931482X" target="_blank">Nachweis im GVK</a>]
2001 about emotion in psychology. In: Emotion review 1 (2009), i. 4, pp. 316–339. 2513 </li><br><li class="biblio" id="elsner_representations_2015">Micha Elsner: Abstract representations
2002 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=559432305" target="_blank">Nachweis im GVK</a>] 2514 of plot structure. In: Linguistic Issues in Language Technology 12 (2015), i.
2003 </li><br><li class="biblio" id="gendron_emotion_2014">Maria Gendron / Debi Roberso / Jacoba&nbsp;Marietta van&nbsp;der Vyver / Lisa&nbsp;Feldman 2515 5. PDF. [<a href="https://aclanthology.org/2015.lilt-12.5/" target="_blank">online</a>]
2004 Barrett: Perceptions of emotion from facial expressions are not culturally universal: 2516 </li><br><li class="biblio" id="elson_networks_2011">David&nbsp;K. Elson / Nicholas Dames / Kathleen&nbsp;R.
2005 Evidence from a remote culture. In: Emotion 14 (2014), i. 2, pp. 251–262. 2517 McKeown: Extracting social networks from literary fiction. In: Proceedings of
2006 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=334290201" target="_blank">Nachweis im GVK</a>] 2518 the 48th Annual Meeting of the Association for Computational Linguistics. (ACL:
2007 </li><br><li class="biblio" id="google_books_2012">Google Books Ngram Viewer. Ed. by Google. In: http://storage.googleapis.com. Version 2519 48, Uppsala, 11.–18.07.2010) Red Hook, NY 2011, pp. 138–147. PDF. [<a href="https://www.aclweb.org/anthology/P10-1015.pdf" target="_blank">online</a>] [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=644235802" target="_blank">Nachweis im GVK</a>]
2008 2. 2012. [<a href="http://storage.googleapis.com/books/ngrams/books/datasetsv2.html" target="_blank">online</a>] 2520 </li><br><li class="biblio" id="emofiel_mpg_2018">EMoFiel: Emotion Mapping of Fictional
2009 </li><br><li class="biblio" id="heise_profiles_1965">David&nbsp;Reuben Jerome Heise: Semantic differential profiles for 1,000 most frequent 2521 Relationship. Ed. by Harshita Jhavar / Paramita Mirza, Max Planck Institute for
2010 English words. In: Psychological Monographs: General and Applied 79 (1965), i. 8, 2522 Informatics. In: mpi-inf.mpg.de. EMoFiel. Saarbrücken 2018. [<a href="https://gate.d5.mpi-inf.mpg.de/emofiel/" target="_blank">online</a>]
2011 pp. 2523 </li><br><li class="biblio" id="francis_corpus_1979">Winthrop Nelson Francis / Henry Kucera: Brown
2012 1–31. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=166710636" target="_blank">Nachweis im GVK</a>] 2524 corpus manual. Preface to revised Edition. Providence, RI 1979. [<a href="http://clu.uni.no/icame/manuals/BROWN/INDEX.HTM" target="_blank">online</a>]
2013 </li><br><li class="biblio" id="henny_exploration_2018">Ulrike Edith&nbsp;Gerda Henny-Krahmer: Exploration of sentiments and genre in Spanish 2525 </li><br><li class="biblio" id="freytag_technik_1863">Gustav Freytag: Die Technik des Dramas.
2014 American novels. In: Digital Humanities 2018: Puentes-Bridges. Book of Abstracts. 2526 Leipzig 1863. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=13347772X" target="_blank">Nachweis im GVK</a>]
2015 Hg. 2527 </li><br><li class="biblio" id="gao_multiscale_2016">Jianbo Gao / Matthew L. Jockers / John Laudun / Timothy Tangherlini: A
2016 von Jonathan Girón Palau / Isabel Galina Russell. (DH 2018, Mexico City, 2528 multiscale theory for the dynamical evolution of sentiment in novels.
2017 26.-29.06.2018) Mexico City 2018, pp. 399–403. PDF. [<a href="https://dh2018.adho.org/wp-content/uploads/2018/06/dh2018_abstracts.pdf" target="_blank">online</a>] 2529 In: International Conference on Behavioral, Economic and Socio-cultural
2018 </li><br><li class="biblio" id="heuser_emotions_216">Ryan Heuser / Franco Moretti / Erik Steiner: The emotions of London. Stanford 2530 Computing (BESC), 2016, pp. 1-4. DOI: <a href="http://dx.doi.org/10.1109/BESC.2016.7804470" target="_blank">10.1109/BESC.2016.7804470</a></li><br><li class="biblio" id="gendrin_past_2009">Maria Gendron / Lisa Feldman&nbsp;Barrett:
2019 2016. (= Literary Lab Pamphlets, 13) PDF.[<a href="https://litlab.stanford.edu/LiteraryLabPamphlet13.pdf" target="_blank">online</a>] 2531 Reconstructing the past: A century of ideas about emotion in psychology. In:
2020 </li><br><li class="biblio" id="historypin_map_2017">Mapping emotions in Victorian London. Ed. by. Historypin. In: historypin.org. New 2532 Emotion review 1 (2009), i. 4, pp. 316–339. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=559432305" target="_blank">Nachweis im GVK</a>]
2021 Orleans et al. 2010-2017. [<a href="https://www.historypin.org/en/victorian-london/geo/51.5128,-0.116085,7/bounds/51.5128,-9.163326,51.5128,8.931156/paging/1" target="_blank">online</a>] 2533 </li><br><li class="biblio" id="gendron_emotion_2014">Maria Gendron / Debi Roberso / Jacoba&nbsp;Marietta
2022 </li><br><li class="biblio" id="miller_text_2014">Hillis J.&nbsp;Miller: Text; Action; Space; Emotion in Conrad’s Nostromo. In: Exploring 2534 van&nbsp;der Vyver / Lisa&nbsp;Feldman Barrett: Perceptions of emotion from facial
2023 Text and Emotions. Ed. by Lars Saetre / Lombardo / Julien Zanetta. Aarhus 2014, pp. 2535 expressions are not culturally universal: Evidence from a remote culture. In:
2024 91–117. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=782781934" target="_blank">Nachweis im GVK</a>] 2536 Emotion 14 (2014), i. 2, pp. 251–262. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=334290201" target="_blank">Nachweis im GVK</a>]
2025 </li><br><li class="biblio" id="hogan_fictions_2010">Patrick&nbsp;Colm Hogan: Fictions and feelings: On the place of literature in the study 2537 </li><br><li class="biblio" id="google_books_2012">Google Books Ngram Viewer. Ed. by Google. In:
2026 of emotion. In: Emotion Review 2 (2010), i. 2, pp. 184–195. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=559432305" target="_blank">Nachweis im GVK</a>] 2538 http://storage.googleapis.com. Version 2. 2012. [<a href="http://storage.googleapis.com/books/ngrams/books/datasetsv2.html" target="_blank">online</a>]
2027 </li><br><li class="biblio" id="hogan_literature_2011">Patrick&nbsp;Colm Hogan: What Literature Teaches Us about Emotion. New York, NY 2011. 2539 </li><br><li class="biblio" id="heise_profiles_1965">David&nbsp;Reuben Jerome Heise: Semantic
2028 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=635158000" target="_blank">Nachweis im GVK</a>] 2540 differential profiles for 1,000 most frequent English words. In: Psychological
2029 </li><br><li class="biblio" id="hoover_studies_2014">David&nbsp;Lowell Hoover / Jonathan Culpeper / Kieran O’Halloran: Digital literary 2541 Monographs: General and Applied 79 (1965), i. 8, pp. 1–31. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=166710636" target="_blank">Nachweis im GVK</a>]
2030 studies: Corpus Approaches to Poetry, Prose, and Drama. New York, NY 2014. 2542 </li><br><li class="biblio" id="henny_exploration_2018">Ulrike Edith&nbsp;Gerda Henny-Krahmer:
2031 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=778221199" target="_blank">Nachweis im GVK</a>] 2543 Exploration of sentiments and genre in Spanish American novels. In: Digital
2032 </li><br><li class="biblio" id="ingermanson_fiction_2009">Randy Ingermanson / Peter Economy. Writing fiction for dummies. Hoboken, NJ 2009. 2544 Humanities 2018: Puentes-Bridges. Book of Abstracts. Hg. von Jonathan Girón
2033 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=686583205" target="_blank">Nachweis im GVK</a>] 2545 Palau / Isabel Galina Russell. (DH 2018, Mexico City, 26.–29.06.2018) Mexico
2034 </li><br><li class="biblio" id="jafri_story_2016">Sajad Jafari / Julien Clinton Sprott / Seyed Mohammad Reza Hashemi Golpayegani: 2546 City 2018, pp. 399–403. PDF. [<a href="https://dh2018.adho.org/wp-content/uploads/2018/06/dh2018_abstracts.pdf" target="_blank">online</a>]
2035 Layla and Majnun: A complex love story. In: Nonlinear Dynamics 83 (2016), i. 1, pp. 2547 </li><br><li class="biblio" id="heuser_emotions_216">Ryan Heuser / Franco Moretti / Erik Steiner:
2036 615–622. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=130936782" target="_blank">Nachweis im GVK</a>] 2548 The emotions of London. Stanford 2016. (= Literary Lab Pamphlets, 13) PDF.[<a href="https://litlab.stanford.edu/LiteraryLabPamphlet13.pdf" target="_blank">online</a>]
2037 </li><br><li class="biblio" id="jhavar_emotions_2018">Harshita Jhavar / Paramita Mirza: EMOFIEL: Mapping emotions of relationships in a 2549 </li><br><li class="biblio" id="historypin_map_2017">Mapping emotions in Victorian London. Ed. by
2038 story. In: Companion Proceedings of the The Web Conference 2018. (WWW’18, Lyon, 2550 Historypin. In: historypin.org. New Orleans et al. 2010–2017. [<a href="https://www.historypin.org/en/victorian-london/geo/51.5128,-0.116085,7/bounds/51.5128,-9.163326,51.5128,8.931156/paging/1" target="_blank">online</a>]
2039 23.-27.04.2018) Geneva 2018, pp. 243–246. DOI: <a href="https://doi.org/10.1145/3184558.3186989" target="_blank">10.1145/3184558.3186989</a></li><br><li class="biblio" id="jockers_humanities_2016">Matthew&nbsp;Lee Jockers / Ted Underwood: Text-mining the humanities. In: A New 2551 </li><br><li class="biblio" id="hogan_fictions_2010">Patrick&nbsp;Colm Hogan: Fictions and feelings: On
2040 Companion to Digital Humanities. Ed. by Susan Schreibman / Ray Siemens / John 2552 the place of literature in the study of emotion. In: Emotion Review 2 (2010),
2041 Unsworth. Pondicherry 2016, pp. 291–306. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=838374875" target="_blank">Nachweis im GVK</a>] 2553 i. 2, pp. 184–195. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=559432305" target="_blank">Nachweis im GVK</a>]
2042 </li><br><li class="biblio" id="johnson_transportation_2012">Dan&nbsp;R. Johnson: Transportation into a story increases empathy, prosocial behavior, 2554 </li><br><li class="biblio" id="hogan_literature_2011">Patrick&nbsp;Colm Hogan: What Literature Teaches
2043 and perceptual bias toward fearful expressions. In: Personality and Individual 2555 Us about Emotion. New York, NY 2011. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=635158000" target="_blank">Nachweis im GVK</a>]
2044 Differences 52 (2012), i. 2, pp. 150–155. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=168042703" target="_blank">Nachweis im GVK</a>] 2556 </li><br><li class="biblio" id="hoover_studies_2014">David&nbsp;Lowell Hoover / Jonathan Culpeper /
2045 </li><br><li class="biblio" id="johnson_language_1989">Philip&nbsp;Nicholas Johnson-Laird / Keith Oatley: The language of emotions: An 2557 Kieran O’Halloran: Digital literary studies: Corpus Approaches to Poetry,
2046 analysis of a semantic field. In: Cognition and emotion 3 (1989), i. 2, pp. 81–123. 2558 Prose, and Drama. New York, NY 2014. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=778221199" target="_blank">Nachweis im GVK</a>]
2047 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=168132915" target="_blank">Nachweis im GVK</a>] 2559 </li><br><li class="biblio" id="ingermanson_fiction_2009">Randy Ingermanson / Peter Economy. Writing
2048 </li><br><li class="biblio" id="johnson_emotions_2016">Philip&nbsp;Nicholas Johnson-Laird / Keith Oatley: Emotions in Music, Literature, and 2560 fiction for dummies. Hoboken, NJ 2009. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=686583205" target="_blank">Nachweis im GVK</a>]
2049 Film. In: Handbook of emotions. Ed. by Lisa Feldman Barret / Michael Lewis / 2561 </li><br><li class="biblio" id="jafri_story_2016">Sajad Jafari / Julien Clinton Sprott / Seyed
2050 Jeannette M. Haviland-Jones. 4. edition. New York, NY et al. 2016. pp. 82–97. 2562 Mohammad Reza Hashemi Golpayegani: Layla and Majnun: A complex love story. In:
2051 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=857367250" target="_blank">Nachweis im GVK</a>] 2563 Nonlinear Dynamics 83 (2016), i. 1, pp. 615–622. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=130936782" target="_blank">Nachweis im GVK</a>]
2052 </li><br><li class="biblio" id="kakkonen_profiles_2011">Tuomo Kakkonen / Gordana Galic&nbsp;Kakkonen: Sentiprofiler: Creating comparable visual 2564 </li><br><li class="biblio" id="jhavar_emotions_2018">Harshita Jhavar / Paramita Mirza: EMOFIEL:
2053 profiles of sentimental content in texts. In: Proceedings of the Workshop on Language 2565 Mapping emotions of relationships in a story. In: Companion Proceedings of the
2054 Technologies for Digital Humanities and Cultural Heritage. Ed. by Cristina Vertan 2566 The Web Conference 2018. (WWW’18, Lyon, 23.–27.04.2018) Geneva 2018, pp.
2055 / Milena Slavcheva / Petya Osenova / Stelios Piperidis. (DigHum / RANLP: 8, Hissar, 2567 243–246. DOI: <a href="https://doi.org/10.1145/3184558.3186989" target="_blank">10.1145/3184558.3186989</a></li><br><li class="biblio" id="jockers_humanities_2016">Matthew&nbsp;Lee Jockers / Ted Underwood:
2056 16.09.2011) Shoumen 2011, pp. 62–69. PDF. [<a href="https://www.aclweb.org/anthology/W11-4110.pdf" target="_blank">online</a>] 2568 Text-mining the humanities. In: A New Companion to Digital Humanities. Ed. by
2057 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=682978558" target="_blank">Nachweis im GVK</a>] 2569 Susan Schreibman / Ray Siemens / John Unsworth. Pondicherry 2016, pp. 291–306.
2058 </li><br><li class="biblio" id="kim_annotation_2018">Evgeny Kim / Roman Klinger: Who feels what and why? Annotation of a literature 2570 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=838374875" target="_blank">Nachweis im GVK</a>]
2059 corpus with semantic roles of emotions. In: Proceedings of the 27th International 2571 </li><br><li class="biblio" id="johnson_transportation_2012">Dan&nbsp;R. Johnson: Transportation into a
2060 Conference on Computational Linguistics. (COLING: 27, Santa Fe, NM, 20.-26.08.2018) 2572 story increases empathy, prosocial behavior, and perceptual bias toward fearful
2061 Stroudsburg, PA 2018, pp. 1345–1359. PDF. [<a href="https://www.aclweb.org/anthology/C18-1114.pdf" target="_blank">online</a>] 2573 expressions. In: Personality and Individual Differences 52 (2012), i. 2, pp.
2062 </li><br><li class="biblio" id="kim_analysis_2019">Evgeny Kim / Roman Klinger (2019a): An analysis of emotion communication channels 2574 150–155. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=168042703" target="_blank">Nachweis im GVK</a>]
2063 in fan-fiction: Towards emotional storytelling. In: Proceedings of the Second 2575 </li><br><li class="biblio" id="johnson_language_1989">Philip&nbsp;Nicholas Johnson-Laird / Keith Oatley:
2064 Workshop of Storytelling. Ed. by Francis Ferraro / Ting-Hao ›Kenneth‹ Huang / Stephanie 2576 The language of emotions: An analysis of a semantic field. In: Cognition and
2065 M. Lukin / Margaret Mitchell. (Florence, 01.08.2019) Stroudsburg, PA 2019. DOI: <a href="http://dx.doi.org/10.18653/v1/W19-3406" target="_blank">10.18653/v1/W19-3406</a></li><br><li class="biblio" id="kim_friendship_2019">Evgeny Kim / Roman Klinger (2019b): Frowning Frodo, wincing Leia, and a seriously 2577 emotion 3 (1989), i. 2, pp. 81–123. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=168132915" target="_blank">Nachweis im GVK</a>]
2066 great friendship: Learning to classify emotional relationships of fictional 2578 </li><br><li class="biblio" id="johnson_emotions_2016">Philip&nbsp;Nicholas Johnson-Laird / Keith Oatley:
2067 characters. In: Proceedings of the 2019 Conference of the North American Chapter of 2579 Emotions in Music, Literature, and Film. In: Handbook of emotions. Ed. by Lisa
2068 the Association for Computational Linguistics: Human Language Technologies. Volume 2580 Feldman Barret / Michael Lewis / Jeannette M. Haviland-Jones. 4. edition. New
2069 1, 2581 York, NY et al. 2016. pp. 82–97. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=857367250" target="_blank">Nachweis im GVK</a>]
2070 Long and Short Papers. (NAACL-HLT, Minneapolis, MN, 02.-07.06.2019) Stroudsburg, PA 2582 </li><br><li class="biblio" id="kakkonen_profiles_2011">Tuomo Kakkonen / Gordana Galic&nbsp;Kakkonen:
2071 2019, pp. 647–653. DOI: <a href="http://dx.doi.org/10.18653/v1/N19-1067" target="_blank">10.18653/v1/N19-1067</a></li><br><li class="biblio" id="kim_relationship_2017">Evgeny Kim / Sebastian Padó / Roman Klinger (2017a): Investigating the 2583 Sentiprofiler: Creating comparable visual profiles of sentimental content in
2072 relationship between literary genres and emotional plot development. In: Joint SIGHUM 2584 texts. In: Proceedings of the Workshop on Language Technologies for Digital
2073 Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, 2585 Humanities and Cultural Heritage. Ed. by Cristina Vertan / Milena Slavcheva /
2074 Humanities and Literature - proceedings of the workshop. (SIGHUM, Vancouver, 04.08.2017) 2586 Petya Osenova / Stelios Piperidis. (DigHum / RANLP: 8, Hissar, 16.09.2011)
2075 Stroudsburg, PA 2017, pp. 17–26. DOI: <a href="http://dx.doi.org/10.18653/v1/W17-2203" target="_blank">10.18653/v1/W17-2203</a></li><br><li class="biblio" id="kim_emotion_2017">Evgeny Kim / Sebastian Padó / Roman Klinger (2017b): Prototypical emotion 2587 Shoumen 2011, pp. 62–69. PDF. [<a href="https://www.aclweb.org/anthology/W11-4110.pdf" target="_blank">online</a>] [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=682978558" target="_blank">Nachweis im GVK</a>]
2076 developments in adventures, romances, and mystery stories. In: Digital Humanities 2588 </li><br><li class="biblio" id="kim_annotation_2018">Evgeny Kim / Roman Klinger: Who feels what and
2077 2017: Conference Abstracts. Ed. by Rhian Lewis / Cecily Raynor / Dominic Forest / 2589 why? Annotation of a literature corpus with semantic roles of emotions. In:
2078 Michael Sinatra / Stéfan Sinclair. (DH 2017, Montreal, 08.-11.08.2017) Montreal 2017, 2590 Proceedings of the 27th International Conference on Computational Linguistics.
2079 pp. 288–291. PDF. [<a href="https://dh2017.adho.org/abstracts/203/203.pdf" target="_blank">online</a>] 2591 (COLING: 27, Santa Fe, NM, 20.–26.08.2018) Stroudsburg, PA 2018, pp. 1345–1359.
2080 </li><br><li class="biblio" id="kim_aspects_2012">Suin Kim / JinYeong Bak / Alice&nbsp;Haeyun Oh: Do you feel what I feel? Social aspects 2592 PDF. [<a href="https://www.aclweb.org/anthology/C18-1114.pdf" target="_blank">online</a>]
2081 of emotions in twitter conversations. In: Proceedings of the Sixth International AAAI 2593 </li><br><li class="biblio" id="kim_analysis_2019">Evgeny Kim / Roman Klinger (2019a): An analysis
2082 Conference on Weblogs and Social Media. (ICWSM: 6, Dublin 04.-07.12.2012) Palo Alto, 2594 of emotion communication channels in fan-fiction: Towards emotional
2083 CA 2012, pp. 495–498. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=734537050" target="_blank">Nachweis im GVK</a>] 2595 storytelling. In: Proceedings of the Second Workshop of Storytelling. Ed. by
2084 </li><br><li class="biblio" id="klinger_emotion_2016">Roman Klinger / Surayya&nbsp;Samat Suliya / Nils Reiter: Automatic Emotion Detection 2596 Francis Ferraro / Ting-Hao ›Kenneth‹ Huang / Stephanie M. Lukin / Margaret
2085 for Quantitative Literary Studies – A case study based on Franz Kafka’s “Das Schloss” 2597 Mitchell. (Florence, 01.08.2019) Stroudsburg, PA 2019. DOI: <a href="http://dx.doi.org/10.18653/v1/W19-3406" target="_blank">10.18653/v1/W19-3406</a></li><br><li class="biblio" id="kim_friendship_2019">Evgeny Kim / Roman Klinger (2019b): Frowning
2086 and “Amerika”. In: Digital Humanities 2016: Conference Abstracts. Ed. by Maciej Eder 2598 Frodo, wincing Leia, and a seriously great friendship: Learning to classify
2087 / Jan Rybicki. (DH 2016, Kraków. 11.-16.07.2016) Kraków 2016, pp. 826–828. PDF. [<a href="https://dh2016.adho.org/abstracts/static/dh2016_abstracts.pdf" target="_blank">online</a>] 2599 emotional relationships of fictional characters. In: Proceedings of the 2019
2088 </li><br><li class="biblio" id="koolen_books_2018">Corina Koolen: Women’s books versus books by women. Digital Humanities 2018: 2600 Conference of the North American Chapter of the Association for Computational
2089 Puentes-Bridges. Book of Abstracts. Hg. von Jonathan Girón Palau / Isabel Galina 2601 Linguistics: Human Language Technologies. Volume 1, Long and Short Papers.
2090 Russell. (DH 2018, Mexico City, 26.-29.06.2018) Mexico City 2018, pp. 219–222. PDF. 2602 (NAACL-HLT, Minneapolis, MN, 02.-07.06.2019) Stroudsburg, PA 2019, pp. 647–653.
2091 [<a href="https://dh2018.adho.org/wp-content/uploads/2018/06/dh2018_abstracts.pdf" target="_blank">online</a>] 2603 DOI: <a href="http://dx.doi.org/10.18653/v1/N19-1067" target="_blank">10.18653/v1/N19-1067</a></li><br><li class="biblio" id="kim_relationship_2017">Evgeny Kim / Sebastian Padó / Roman Klinger
2092 </li><br><li class="biblio" id="kracier_characters_2019">Eve Kraicer / Andrew Piper: Social characters: The hierarchy of gender in 2604 (2017a): Investigating the relationship between literary genres and emotional
2093 contemporary English-language fiction. In: Journal of Cultural Analytics (2019). 2605 plot development. In: Joint SIGHUM Workshop on Computational Linguistics for
2094 Article from 30.01.2019. DOI: <a href="http://doi.org/10.22148/16.032" target="_blank">10.22148/16.032</a></li><br><li class="biblio" id="kuivalainen_emotions_2009">Päivi Kuivalainen: Emotions in narrative: A linguistic study of Katherine 2606 Cultural Heritage, Social Sciences, Humanities and Literature – proceedings of
2095 Mansfield’s short fiction. In: The Electronic Journal of the Department of English 2607 the workshop. (SIGHUM, Vancouver, 04.08.2017) Stroudsburg, PA 2017, pp. 17–26.
2096 at 2608 DOI: <a href="http://dx.doi.org/10.18653/v1/W17-2203" target="_blank">10.18653/v1/W17-2203</a></li><br><li class="biblio" id="kim_emotion_2017">Evgeny Kim / Sebastian Padó / Roman Klinger
2097 the University of Helsinki 5 (2009). [<a href="https://blogs.helsinki.fi/hes-eng/volumes/volume-5/emotions-in-narrative-a-linguistic-study-of-katherine-mansfield%E2%80%99s-short-fiction-paivi-kuivalainen/" target="_blank">online</a>] 2609 (2017b): Prototypical emotion developments in adventures, romances, and mystery
2098 </li><br><li class="biblio" id="lanham_word_1989">Richard&nbsp;A. Lanham: The electronic word: Literary study and the digital revolution. 2610 stories. In: Digital Humanities 2017: Conference Abstracts. Ed. by Rhian Lewis
2099 In: New Literary History 20 (1989), i. 2, pp. 265–290. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129093378" target="_blank">Nachweis im GVK</a>] 2611 / Cecily Raynor / Dominic Forest / Michael Sinatra / Stéfan Sinclair. (DH 2017,
2100 </li><br><li class="biblio" id="larsen_promises_1992">Randy&nbsp;J. Larsen / Edward Diener: Promises and problems with the circumplex model 2612 Montreal, 08.–11.08.2017) Montreal 2017, pp. 288–291. PDF. [<a href="https://dh2017.adho.org/abstracts/203/203.pdf" target="_blank">online</a>]
2101 of emotion. In: Emotion. Ed. by Margaret S. Clark. (= Review of personality and 2613 </li><br><li class="biblio" id="kim_aspects_2012">Suin Kim / JinYeong Bak / Alice&nbsp;Haeyun Oh: Do you
2102 social psychology, 13) Newbury Park et al. 1992, pp. 25–29. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=019245793" target="_blank">Nachweis im GVK</a>] 2614 feel what I feel? Social aspects of emotions in twitter conversations. In:
2103 </li><br><li class="biblio" id="leemans_emotions_2017">Inger Leemans / Janneke&nbsp;M. van&nbsp;der Zwaan / Isa Maks / Erika Kuijpers / Kristine 2615 Proceedings of the Sixth International AAAI Conference on Weblogs and Social
2104 Steenbergh: Mining embodied emotions: a comparative analysis of sentiment and emotion 2616 Media. (ICWSM: 6, Dublin 04.-07.12.2012) Palo Alto, CA 2012, pp. 495–498. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=734537050" target="_blank">Nachweis im GVK</a>]
2105 in dutch texts, 1600–1800. In: Digital Humanities Quaterly 11 (2017), i. 4. [<a href="http://www.digitalhumanities.org/dhq/vol/11/4/000343/000343.html" target="_blank">online</a>] 2617 </li><br><li class="biblio" id="klinger_emotion_2016">Roman Klinger / Surayya&nbsp;Samat Suliya / Nils
2106 </li><br><li class="biblio" id="liu_opinions_2015">Bing Liu: Sentiment Analysis: mining opinions, sentiments, and emotions. New York, 2618 Reiter: Automatic Emotion Detection for Quantitative Literary Studies – A case
2107 NY 2015. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=797283382" target="_blank">Nachweis im GVK</a>] 2619 study based on Franz Kafka’s “Das Schloss” and “Amerika”. In: Digital
2108 </li><br><li class="biblio" id="liu_analysis_2010">Bing Liu: Sentiment analysis and subjectivity. In: Handbook of natural language 2620 Humanities 2016: Conference Abstracts. Ed. by Maciej Eder / Jan Rybicki. (DH
2109 processing. Ed. by Nitin Indurkhya / Fred Jacob Damerau. 2. edition. Boca Raton, FL 2621 2016, Kraków. 11.–16.07.2016) Kraków 2016, pp. 826–828. PDF. [<a href="https://dh2016.adho.org/abstracts/static/dh2016_abstracts.pdf" target="_blank">online</a>]
2110 2010, pp. 627–666. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=611246643" target="_blank">Nachweis im GVK</a>] 2622 </li><br><li class="biblio" id="koolen_books_2018">Corina Koolen: Women’s books versus books by
2111 </li><br><li class="biblio" id="maentylae_evolution_2018">Mika&nbsp;V. Mäntylä / Daniel Graziotin / Miikka Kuutila: The evolution of sentiment 2623 women. Digital Humanities 2018: Puentes-Bridges. Book of Abstracts. Hg. von
2112 analysis – a review of research topics, venues, and top cited papers. In: Computer 2624 Jonathan Girón Palau / Isabel Galina Russell. (DH 2018, Mexico City,
2113 Science Review 27 (2018), pp. 16–32. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=608051535" target="_blank">Nachweis im GVK</a>] 2625 26.–29.06.2018) Mexico City 2018, pp. 219–222. PDF. [<a href="https://dh2018.adho.org/wp-content/uploads/2018/06/dh2018_abstracts.pdf" target="_blank">online</a>]
2114 </li><br><li class="biblio" id="mar_emotion_2011">Raymond&nbsp;A. Mar / Keith Oatley / Maja Djikic / Justin Mullin: Emotion and narrative 2626 </li><br><li class="biblio" id="kraicer_characters_2019">Eve Kraicer / Andrew Piper: Social
2115 fiction: Interactive influences before, during, and after reading. In: Cognition 2627 characters: The hierarchy of gender in contemporary English-language fiction.
2116 &amp; Emotion 25 (2011), i. 5, pp. 818–833. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=168132915" target="_blank">Nachweis im GVK</a>] 2628 In: Journal of Cultural Analytics (2019). Article from 30.01.2019. DOI: <a href="http://doi.org/10.22148/16.032" target="_blank">10.22148/16.032</a></li><br><li class="biblio" id="kuivalainen_emotions_2009">Päivi Kuivalainen: Emotions in narrative:
2117 </li><br><li class="biblio" id="marchetti_analysis_2014">Alessandro Marchetti / Rachele Sprugnoli / Sara Tonelli: Sentiment analysis for 2629 A linguistic study of Katherine Mansfield’s short fiction. In: The Electronic
2118 the humanities: the case of historical texts. In: Digital Humanities 2014: Conference 2630 Journal of the Department of English at the University of Helsinki 5 (2009).
2119 Abstracts. (DH 2014, Lausanne 08.-12.07.2014), Lausanne 2014, pp. 254–257. PDF. [<a href="https://dh2014.files.wordpress.com/2014/07/dh2014_abstracts_proceedings_07-11.pdf" target="_blank">online</a>] [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=797245014" target="_blank">Nachweis im GVK</a>] 2631 [<a href="https://blogs.helsinki.fi/hes-eng/volumes/volume-5/emotions-in-narrative-a-linguistic-study-of-katherine-mansfield%E2%80%99s-short-fiction-paivi-kuivalainen/" target="_blank">online</a>]
2120 </li><br><li class="biblio" id="marvel_model_2011">Seth&nbsp;A. Marvel / Jon Kleinberg / Robert&nbsp;D. Kleinberg / Steven&nbsp;H. Strogatz: 2632 </li><br><li class="biblio" id="lanham_word_1989">Richard&nbsp;A. Lanham: The electronic word: Literary
2121 Continuous-time model of structural balance. In: Proceedings of the National Academy 2633 study and the digital revolution. In: New Literary History 20 (1989), i. 2, pp.
2122 of Sciences 108 (2011), i. 5, pp. 1771–1776. DOI: <a href="https://doi.org/10.1073/pnas.1013213108" target="_blank">10.1073/pnas.1013213108</a> [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129505269" target="_blank">Nachweis im GVK</a>] 2634 265–290. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129093378" target="_blank">Nachweis im GVK</a>]
2123 </li><br><li class="biblio" id="mayer_abilities_2008">John&nbsp;D. Mayer / Richard&nbsp;D. Roberts / Sigal&nbsp;G. Barsade: Human abilities: Emotional 2635 </li><br><li class="biblio" id="larsen_promises_1992">Randy&nbsp;J. Larsen / Edward Diener: Promises and
2124 intelligence. In: Annual Review of Psychology 59 (2008), i. 1, pp. 507–536. 2636 problems with the circumplex model of emotion. In: Emotion. Ed. by Margaret S.
2125 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129499366" target="_blank">Nachweis im GVK</a>] 2637 Clark. (= Review of personality and social psychology, 13) Newbury Park et al.
2126 </li><br><li class="biblio" id="meel_emotions_1995">Jacques&nbsp;M. van Meel: Representing emotions in literature and paintings: a 2638 1992, pp. 25–29. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=019245793" target="_blank">Nachweis im GVK</a>]
2127 comparative analysis. In: Poetics 23 (1995), i. 1–2, pp. 159–176. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129289507" target="_blank">Nachweis im GVK</a>] 2639 </li><br><li class="biblio" id="leemans_emotions_2017">Inger Leemans / Janneke&nbsp;M. van&nbsp;der Zwaan /
2128 </li><br><li class="biblio" id="mohammad_time_2011">Saif M. Mohammad: From once upon a time to happily ever after: Tracking emotions 2640 Isa Maks / Erika Kuijpers / Kristine Steenbergh: Mining embodied emotions: a
2129 in novels and fairy tales. In: Proceedings of the 5th ACL-HLT Workshop on Language 2641 comparative analysis of sentiment and emotion in dutch texts, 1600–1800. In:
2130 Technology for Cultural Heritage, Social Sciences, and Humanities. Ed. by Kalliopi 2642 Digital Humanities Quarterly 11 (2017), i. 4. [<a href="http://www.digitalhumanities.org/dhq/vol/11/4/000343/000343.html" target="_blank">online</a>]
2131 Zervanou /&nbsp;Piroska Lendvai. (ACL-HT: 5, Portland, OR, 23.-24.06.2011) Stroudsburg, 2643 </li><br><li class="biblio" id="liu_opinions_2015">Bing Liu: Sentiment Analysis: mining opinions,
2132 PA 2644 sentiments, and emotions. New York, NY 2015. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=797283382" target="_blank">Nachweis im GVK</a>]
2133 2011, pp. 105–114. PDF. [<a href="https://www.aclweb.org/anthology/W11-1514.pdf" target="_blank">online</a>] 2645 </li><br><li class="biblio" id="liu_analysis_2010">Bing Liu: Sentiment analysis and subjectivity.
2134 </li><br><li class="biblio" id="mohammad_time_2012">Saif&nbsp;M. Mohammad: From once upon a time to happily ever after: Tracking emotions 2646 In: Handbook of natural language processing. Ed. by Nitin Indurkhya / Fred
2135 in mail and books. In: Decision Support Systems 53 (2012), i. 4, pp. 730–741. 2647 Jacob Damerau. 2. edition. Boca Raton, FL 2010, pp. 627–666. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=611246643" target="_blank">Nachweis im GVK</a>]
2136 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129176532" target="_blank">Nachweis im GVK</a>] 2648 </li><br><li class="biblio" id="maentylae_evolution_2018">Mika&nbsp;V. Mäntylä / Daniel Graziotin /
2137 </li><br><li class="biblio" id="mohammad_crowdsourcing_2013">Saif&nbsp;M. Mohammad / Peter&nbsp;D. Turney: Crowdsourcing a word–emotion association 2649 Miikka Kuutila: The evolution of sentiment analysis – a review of research
2138 lexicon. In: Computational Intelligence 29 (2013), i. 3, pp. 436–465. 2650 topics, venues, and top cited papers. In: Computer Science Review 27 (2018),
2139 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129176370" target="_blank">Nachweis im GVK</a>] 2651 pp. 16–32. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=608051535" target="_blank">Nachweis im GVK</a>]
2140 </li><br><li class="biblio" id="moretti_graphs_2005">Franco Moretti: Graphs, maps, trees: abstract models for a literary history. 2652 </li><br><li class="biblio" id="mar_emotion_2011">Raymond&nbsp;A. Mar / Keith Oatley / Maja Djikic /
2141 London et al. 2005. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=47948466X" target="_blank">Nachweis im GVK</a>] 2653 Justin Mullin: Emotion and narrative fiction: Interactive influences before,
2142 </li><br><li class="biblio" id="morin_birth_2017">Olivier Morin / Alberto Acerbi: Birth of the cool: a two-centuries decline in 2654 during, and after reading. In: Cognition &amp; Emotion 25 (2011), i. 5, pp.
2143 emotional expression in anglophone fiction. In: Cognition and Emotion 31 (2017), i. 2655 818–833. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=168132915" target="_blank">Nachweis im GVK</a>]
2144 8, pp. 1663–1675. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=168132915" target="_blank">Nachweis im GVK</a>] 2656 </li><br><li class="biblio" id="marchetti_analysis_2014">Alessandro Marchetti / Rachele Sprugnoli /
2145 </li><br><li class="biblio" id="nalisnick_analysis_2013">Eric&nbsp;T. Nalisnick / Henry&nbsp;S. Baird (2013a): Character-to-character sentiment 2657 Sara Tonelli: Sentiment analysis for the humanities: the case of historical
2146 analysis in shakespeare’s plays. In: Proceedings of the 51st Annual Meeting of the 2658 texts. In: Digital Humanities 2014: Conference Abstracts. (DH 2014, Lausanne
2147 Association for Computational Linguistics. Ed. by Hinrich Schuetze /&nbsp;Pascale Fung 2659 08.-12.07.2014), Lausanne 2014, pp. 254–257. PDF. [<a href="https://dh2014.files.wordpress.com/2014/07/dh2014_abstracts_proceedings_07-11.pdf" target="_blank">online</a>] [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=797245014" target="_blank">Nachweis im GVK</a>]
2148 /&nbsp;Massimo Poesio. 3 volumes. (ACL: 51, Sofia, 04.-09.08.2013) Red Hook, NY et al. 2660 </li><br><li class="biblio" id="marvel_model_2011">Seth&nbsp;A. Marvel / Jon Kleinberg / Robert&nbsp;D.
2149 2013. Vol. 2: Short Papers, pp. 479–483. [<a href="https://www.aclweb.org/anthology/P13-2085.pdf" target="_blank">online</a>] 2661 Kleinberg / Steven&nbsp;H. Strogatz: Continuous-time model of structural balance.
2150 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=770778011" target="_blank">Nachweis im GVK</a>] 2662 In: Proceedings of the National Academy of Sciences 108 (2011), i. 5, pp.
2151 </li><br><li class="biblio" id="nalisnick_networs_2013">Eric&nbsp;T. Nalisnick / Henry&nbsp;S. Baird (2013b): Extracting sentiment networks from 2663 1771–1776. DOI: <a href="https://doi.org/10.1073/pnas.1013213108" target="_blank">10.1073/pnas.1013213108</a> [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129505269" target="_blank">Nachweis im GVK</a>]
2152 shakespeare’s plays. In: 12th International Conference on Document Analysis and 2664 </li><br><li class="biblio" id="mauss_measures_2009">Iris B. Mauss / Michael D. Robinson: Measures of emotion: A review.
2153 Recognition. (ICDAR: 12, Washington, DC, 25.-28.08.2013) Piscataway, NJ 2013, pp. 2665 In: Cognition and Emotion 23 (2009), pp. 209–237. DOI:
2154 758–762. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=776401467" target="_blank">Nachweis im GVK</a>] 2666 <a href="https://doi.org/10.1080/02699930802204677" target="_blank">10.1080/02699930802204677</a> [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=168132915" target="_blank">Nachweis im GVK</a>]
2155 </li><br><li class="biblio" id="nielsen_lexicon_2011">Finn&nbsp;Årup&nbsp;Nielsen: AFINN Sentiment Lexicon. In: corpustext.com. 2011. [<a href="http://corpustext.com/reference/sentiment_afinn.html" target="_blank">online</a>] 2667 </li><br><li class="biblio" id="mayer_abilities_2008">John&nbsp;D. Mayer / Richard&nbsp;D. Roberts / Sigal&nbsp;G.
2156 </li><br><li class="biblio" id="oliver_states_2008">Mary&nbsp;Beth Oliver: Tender affective states as predictors of entertainment 2668 Barsade: Human abilities: Emotional intelligence. In: Annual Review of
2157 preference. In: Journal of Communication 58 (2008), i. 1, pp. 40–61. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129078212" target="_blank">Nachweis im GVK</a>] 2669 Psychology 59 (2008), i. 1, pp. 507–536. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129499366" target="_blank">Nachweis im GVK</a>]
2158 </li><br><li class="biblio" id="patti_explration_2015">Viviana Patti / Federico Bertola / Antonio Lieto: Arsemotica for arsmeteo.org: 2670 </li><br><li class="biblio" id="mellmann_emotion_2002">Katja Mellmann: E-Motion: Being Moved by Fiction and Media? Notes on
2159 Emotion-driven exploration of online art collections. In: The Twenty-Eighth 2671 Fictional Worlds, Virtual Contacts and the Reality of Emotions. In:
2160 International Florida Artificial Intelligence Research Society Conference. Ed. by 2672 PsyArt (2002). Article from 29.10.2002. [<a href="https://www.psyartjournal.com/article/show/mellmann-e_motion_being_moved_by_fiction_and_medi" target="_blank">online</a>]
2161 Ingrid Russell / William Eberle. (FLAIRS: 28, Hollywood, 18.-28.05.2015) Palo Alto, 2673 </li><br><li class="biblio" id="meel_emotions_1995">Jacques&nbsp;M. van Meel: Representing emotions in
2162 CA, pp. 288–293. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=862385458" target="_blank">Nachweis im GVK</a>] 2674 literature and paintings: a comparative analysis. In: Poetics 23 (1995), i.
2163 </li><br><li class="biblio" id="pennebaker_development_2007">James W. Pennebaker / Cindy K.&nbsp;Chung / Molly&nbsp;Ireland / Amy&nbsp;Gonzales / Roger 2675 1–2, pp. 159–176. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129289507" target="_blank">Nachweis im GVK</a>]
2164 J.&nbsp;Booth: The development and psychometric properties of LIWC2007. In: LIWC2007 2676 </li><br><li class="biblio" id="miller_text_2014">Joseph Hillis&nbsp;Miller: Text; Action; Space; Emotion in Conrad’s Nostromo.
2165 Manual. liwc.net. 2007. PDF. [<a href="http://www.liwc.net/LIWC2007LanguageManual.pdf" target="_blank">online</a>] 2677 In: Exploring Text and Emotions. Ed. by Lars Saetre / Lombardo / Julien
2166 </li><br><li class="biblio" id="pianta_database_2002">Emanuele Pianta / Luisa Bentivogli / Christian Girardi: MultiWordNet: Developing 2678 Zanetta. Aarhus 2014, pp. 91–117. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129289507" target="_blank">Nachweis im GVK</a>]
2167 an aligned multilingual database. In: Proceedings of 1st International Global WordNet 2679 </li><br><li class="biblio" id="mohammad_time_2011">Saif M. Mohammad: From once upon a time to
2168 Conference. (GWC: 1, Mysore, 21.-25.02.2002) Mysore 2002, pp. 293–302. [<a href="http://multiwordnet.fbk.eu/paper/MWN-India-published.pdf" target="_blank">online</a>] 2680 happily ever after: Tracking emotions in novels and fairy tales. In:
2169 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=357991133" target="_blank">Nachweis im GVK</a>] 2681 Proceedings of the 5th ACL-HLT Workshop on Language Technology for Cultural
2170 </li><br><li class="biblio" id="piper_bestseller_2015">Andrew Piper / Richard Jean&nbsp;So: Quantifying the weepy bestseller. In: The New 2682 Heritage, Social Sciences, and Humanities. Ed. by Kalliopi Zervanou /&nbsp;Piroska
2171 Rebublic. Article from 18.12.2015. [<a href="https://newrepublic.com/article/126123/quantifying-weepy-bestseller" target="_blank">online</a>] 2683 Lendvai. (ACL-HT: 5, Portland, OR, 23.–24.06.2011) Stroudsburg, PA 2011, pp.
2172 </li><br><li class="biblio" id="plato_volumes_1969">Plato: Plato in Twelve Volumes. Cambridge, MA 1969. Siehe auch [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=150154208" target="_blank">Nachweis im GVK</a>] 2684 105–114. PDF. [<a href="https://www.aclweb.org/anthology/W11-1514.pdf" target="_blank">online</a>]
2173 </li><br><li class="biblio" id="posner_model_2005">Jonathan Posner / James Russell / Bradley Peterson: The circumplex model of affect: 2685 </li><br><li class="biblio" id="mohammad_time_2012">Saif&nbsp;M. Mohammad: From once upon a time to
2174 An integrative approach to affective neuroscience, cognitive development, and psychopathology. 2686 happily ever after: Tracking emotions in mail and books. In: Decision Support
2175 In: Development and psychopathology 17 (2005), i. 3, pp. 715-734. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=170289036" target="_blank">Nachweis im GVK</a>] 2687 Systems 53 (2012), i. 4, pp. 730–741. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129176532" target="_blank">Nachweis im GVK</a>]
2176 </li><br><li class="biblio" id="plutchik_emotions_1991">Robert Plutchik: The Emotions. Revided edition. Lanham et al. 1991. 2688 </li><br><li class="biblio" id="mohammad_crowdsourcing_2013">Saif&nbsp;M. Mohammad / Peter&nbsp;D. Turney:
2177 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=113543220" target="_blank">Nachweis im GVK</a>] 2689 Crowdsourcing a word–emotion association lexicon. In: Computational
2178 </li><br><li class="biblio" id="plutchik_wheel_2011">Robert Plutchik: Wheel of Emotions, 12.02.2011. In: Wikipedia, the free Encyclopedia: 2690 Intelligence 29 (2013), i. 3, pp. 436–465. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129176370" target="_blank">Nachweis im GVK</a>]
2179 Robert 2691 </li><br><li class="biblio" id="moretti_graphs_2005">Franco Moretti: Graphs, maps, trees: abstract
2180 Plutchik. Article from 20.09.2019. [<a href="https://en.wikipedia.org/wiki/Robert_Plutchik#/media/File:Plutchik-wheel.svg" target="_blank">online</a>] 2692 models for a literary history. London et al. 2005. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=47948466X" target="_blank">Nachweis im GVK</a>]
2181 </li><br><li class="biblio" id="project_gutenberg_2019">Project Gutenberg. Ed. by Project Gutenberg Literary Archive Foundation. In: gutenberg.org. 2693 </li><br><li class="biblio" id="morin_birth_2017">Olivier Morin / Alberto Acerbi: Birth of the cool:
2182 Salt Lake City, UT 1971-. [<a href="https://www.gutenberg.org" target="_blank">online</a>] 2694 a two-centuries decline in emotional expression in anglophone fiction. In:
2183 </li><br><li class="biblio" id="reagan_arcs_2016">Andrew&nbsp;J. Reagan / Lewis Mitchell / Dilan Kiley / Christopher&nbsp;M. Danforth / 2695 Cognition and Emotion 31 (2017), i. 8, pp. 1663–1675. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=168132915" target="_blank">Nachweis im GVK</a>]
2184 Peter&nbsp;Sheridan Dodds: The emotional arcs of stories are dominated by six basic 2696 </li><br><li class="biblio" id="nalisnick_analysis_2013">Eric&nbsp;T. Nalisnick / Henry&nbsp;S. Baird (2013a):
2185 shapes. In: EPJ Data Science 5 (2016), i. 1, pp. 31–43. DOI: <a href="https://doi.org/10.1140/epjds/s13688-016-0093-1" target="_blank">10.1140/epjds/s13688-016-0093-1</a></li><br><li class="biblio" id="reed_poetry_2018">Ethan Reed: Measured unrest in the poetry of the black arts movement. Digital 2697 Character-to-character sentiment analysis in shakespeare’s plays. In:
2186 Humanities 2018: Puentes-Bridges. Book of Abstracts. Hg. von Jonathan Girón Palau 2698 Proceedings of the 51st Annual Meeting of the Association for Computational
2187 / 2699 Linguistics. Ed. by Hinrich Schuetze /&nbsp;Pascale Fung /&nbsp;Massimo Poesio. 3
2188 Isabel Galina Russell. (DH 2018, Mexico City, 26.-29.06.2018) Mexico City 2018, pp. 2700 volumes. (ACL: 51, Sofia, 04.–09.08.2013) Red Hook, NY et al. 2013. Vol. 2:
2189 477–478. PDF. [<a href="https://dh2018.adho.org/wp-content/uploads/2018/06/dh2018_abstracts.pdf" target="_blank">online</a>] 2701 Short Papers, pp. 479–483. [<a href="https://www.aclweb.org/anthology/P13-2085.pdf" target="_blank">online</a>] [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=770778011" target="_blank">Nachweis im GVK</a>]
2190 </li><br><li class="biblio" id="reman_corpus_2019">REMAN - Relational Emotion Annotation for Fiction. Relational EMotion ANnotation – 2702 </li><br><li class="biblio" id="nalisnick_networks_2013">Eric&nbsp;T. Nalisnick / Henry&nbsp;S. Baird (2013b):
2191 a corpus with 1720 fictional text exceprts from the Project Gutenberg. 2703 Extracting sentiment networks from shakespeare’s plays. In: 12th International
2192 Ed. by Evgeny Kim / Roman Klinger, Universität Stuttgart, Institut für Maschinelle 2704 Conference on Document Analysis and Recognition. (ICDAR: 12, Washington, DC,
2193 Sprachverarbeitung. In: ims.uni-stuttgart.de. Institut für Maschinelle Sprachverarbeitung. 2705 25.–28.08.2013) Piscataway, NJ 2013, pp. 758–762. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=776401467" target="_blank">Nachweis im GVK</a>]
2194 Forschung. Ressourcen 2706 </li><br><li class="biblio" id="nielsen_lexicon_2011">Finn&nbsp;Årup&nbsp;Nielsen: AFINN Sentiment Lexicon.
2195 Korpora. Stuttgart 2018. [<a href="http://www.ims.uni-stuttgart.de/data/reman" target="_blank">online</a>] 2707 In: corpustext.com. 2011. [<a href="http://corpustext.com/reference/sentiment_afinn.html" target="_blank">online</a>]
2196 </li><br><li class="biblio" id="richins_emotions_1997">Marsha&nbsp;L. Richins: Measuring emotions in the consumption experience. In: Journal 2708 </li><br><li class="biblio" id="oberlaender_experiencers">Laura Ana Maria Oberländer / Kevin Reich / Roman Klinger:
2197 of consumer research 24 (1997), i. 2, pp. 127–146. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129412023" target="_blank">Nachweis im GVK</a>] 2709 Experiencers, Stimuli, or Targets: Which Semantic Roles Enable Machine
2198 </li><br><li class="biblio" id="rinaldi_discoveries_2013">Sergio Rinaldi / Pietro Landi / Fabio Della Rossa: Small discoveries can have 2710 Learning to Infer the Emotions? In: Proceedings of the Third Workshop on
2199 great consequences in love affairs: the case of Beauty and the Beast. In: 2711 Computational Modeling of People's Opinions, Personality, and Emotion's
2200 International Journal of Bifurcation and Chaos 23 (2013), i. 11. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=130955957" target="_blank">Nachweis im GVK</a>] 2712 in Social Media. Barcelona 2020, pp. 119–128. [<a href="https://www.aclanthology.org/2020.peoples-1.12/" target="_blank">online</a>]
2201 </li><br><li class="biblio" id="robinson_reason_2005">Jenefer Robinson: Deeper than reason: Emotion and its role in literature, music, 2713 </li><br><li class="biblio" id="oliver_states_2008">Mary&nbsp;Beth Oliver: Tender affective states as
2202 and art. New York, NY 2005. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=476217229" target="_blank">Nachweis im GVK</a>] 2714 predictors of entertainment preference. In: Journal of Communication 58 (2008),
2203 </li><br><li class="biblio" id="ross_encounter_1999">Catherine&nbsp;Sheldrick Ross: Finding without seeking: the information encounter in 2715 i. 1, pp. 40–61. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129078212" target="_blank">Nachweis im GVK</a>]
2204 the context of reading for pleasure. In: Information Processing &amp; Management 35 2716 </li><br><li class="biblio" id="patti_exploration_2015">Viviana Patti / Federico Bertola / Antonio
2205 (1999), i. 6., pp. 783–799. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129428205" target="_blank">Nachweis im GVK</a>] 2717 Lieto: Arsemotica for arsmeteo.org: Emotion-driven exploration of online art
2206 </li><br><li class="biblio" id="russel_model_1980">James&nbsp;A. Russell: A circumplex model of affect. In: Journal of Personality and 2718 collections. In: The Twenty-Eighth International Florida Artificial
2207 Social Psychology 39 (1980), pp. 1161–1178. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129078964" target="_blank">Nachweis im GVK</a>] 2719 Intelligence Research Society Conference. Ed. by Ingrid Russell / William
2208 </li><br><li class="biblio" id="russel_recognition_1994">James&nbsp;A. Russell: Is there universal recognition of emotion from facial 2720 Eberle. (FLAIRS: 28, Hollywood, 18.–28.05.2015) Palo Alto, CA, pp. 288–293.
2209 expression? A review of the cross-cultural studies. In: Psychological bulletin 115 2721 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=862385458" target="_blank">Nachweis im GVK</a>]
2210 (1994), i. 1, pp. 102–141. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129067016" target="_blank">Nachweis im GVK</a>] 2722 </li><br><li class="biblio" id="pennebaker_development_2007">James W. Pennebaker / Cindy K.&nbsp;Chung /
2211 </li><br><li class="biblio" id="russel_affect_2003">James&nbsp;A. Russell: Core affect and the psychological construction of emotion. In: 2723 Molly&nbsp;Ireland / Amy&nbsp;Gonzales / Roger J.&nbsp;Booth: The development and psychometric
2212 Psychological review 110 (2003), i. 1, pp. 145–172. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129509493" target="_blank">Nachweis im GVK</a>] 2724 properties of LIWC2007. In: LIWC2007 Manual. liwc.net. 2007. PDF. [<a href="http://www.liwc.net/LIWC2007LanguageManual.pdf" target="_blank">online</a>]
2213 </li><br><li class="biblio" id="russel_affect_1999">James&nbsp;A. Russell / Lisa&nbsp;Feldman Barrett: Core affect, prototypical emotional 2725 </li><br><li class="biblio" id="pianta_database_2002">Emanuele Pianta / Luisa Bentivogli / Christian
2214 episodes, and other things called emotion: dissecting the elephant. In: Journal of 2726 Girardi: MultiWordNet: Developing an aligned multilingual database. In:
2215 Personality and Social Psychology 76 (1999), i. 5, pp. 805–819. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129078964" target="_blank">Nachweis im GVK</a>] 2727 Proceedings of 1st International Global WordNet Conference. (GWC: 1, Mysore,
2216 </li><br><li class="biblio" id="russel_expressions_2003">James&nbsp;A. Russell / Jo-Anne Bachorowski / José-Miguel Fernández-Dols: Facial and 2728 21.–25.02.2002) Mysore 2002, pp. 293–302. [<a href="http://multiwordnet.fbk.eu/paper/MWN-India-published.pdf" target="_blank">online</a>] [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=357991133" target="_blank">Nachweis im GVK</a>]
2217 vocal expressions of emotion. In: Annual review of psychology 54 (2003), i. 1, pp. 2729 </li><br><li class="biblio" id="piper_bestseller_2015">Andrew Piper / Richard Jean&nbsp;So: Quantifying
2218 329–349. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129499366" target="_blank">Nachweis im GVK</a>] 2730 the weepy bestseller. In: The New Rebublic. Article from 18.12.2015. [<a href="https://newrepublic.com/article/126123/quantifying-weepy-bestseller" target="_blank">online</a>]
2219 </li><br><li class="biblio" id="saetre_exploring_2014">Exploring Text and Emotions. Ed. by Lars Sætre / Patrizia Lombardo / Julien 2731 </li><br><li class="biblio" id="plato_volumes_1969">Plato: Plato in Twelve Volumes. Cambridge, MA
2220 Zanetta (2014a). Aarhus 2014. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=782781934" target="_blank">Nachweis im GVK</a>] 2732 1969. Siehe auch [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=150154208" target="_blank">Nachweis im GVK</a>]
2221 </li><br><li class="biblio" id="saetre_text_2014">Lars Sætre / Patrizia Lombardo / Julien Zanetta (2014b): Text and Emotions. In: 2733 </li><br><li class="biblio" id="posner_model_2005">Jonathan Posner / James Russell / Bradley
2222 Exploring Text and Emotions. Ed. by Lars Sætre / Patrizia Lombardo / Julien Zanetta. 2734 Peterson: The circumplex model of affect: An integrative approach to affective
2223 Aarhus 2014, pp. 9–26. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=782781934" target="_blank">Nachweis im GVK</a>] 2735 neuroscience, cognitive development, and psychopathology. In: Development and
2224 </li><br><li class="biblio" id="samothrakis_annotation_2015">Spyridon Samothrakis / Maria Fasli: Emotional sentence annotation helps predict 2736 psychopathology 17 (2005), i. 3, pp. 715–734. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=170289036" target="_blank">Nachweis im GVK</a>]
2225 fiction genre. In: PLOS ONE 10 (2015), i. 11, p. e0141922. Article from 02.11.2015. 2737 </li><br><li class="biblio" id="plutchik_emotions_1991">Robert Plutchik: The Emotions. Revided
2226 DOI: <a href="https://doi.org/10.1371/journal.pone.0141922" target="_blank">10.1371/journal.pone.0141922</a></li><br><li class="biblio" id="samur_session_2018">Dalya Samur / Mattie Tops / Sander&nbsp;L. Koole: Does a single session of reading 2738 edition. Lanham et al. 1991. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=113543220" target="_blank">Nachweis im GVK</a>]
2227 literary fiction prime enhanced mentalising performance? Four replication experiments 2739 </li><br><li class="biblio" id="plutchik_wheel_2011">Robert Plutchik: Wheel of Emotions, 12.02.2011.
2228 of Kidd and Castano (2013). In: Cognition &amp; Emotion 32 (2018), pp. 130–144. 2740 In: Wikipedia, the free Encyclopedia: Robert Plutchik. Article from 20.09.2019.
2229 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=168132915" target="_blank">Nachweis im GVK</a>] 2741 [<a href="https://en.wikipedia.org/wiki/Robert_Plutchik#/media/File:Plutchik-wheel.svg" target="_blank">online</a>]
2230 </li><br><li class="biblio" id="scarantino_phylosophy_2016">Andrea Scarantino: The Phylosophy of Emotions and Its Impact on Affective 2742 </li><br><li class="biblio" id="project_gutenberg_2019">Project Gutenberg. Ed. by Project Gutenberg
2231 Sciences. In: Handbook of emotions. Ed. by Lisa Feldman Barret / Michael Lewis / 2743 Literary Archive Foundation. In: gutenberg.org. Salt Lake City, UT 1971–. <a href="https://www.gutenberg.org" target="_blank">https://www.gutenberg.org</a>. [<i>Webseite aus Deutschland nicht mehr erreichbar</i>]
2232 Jeannette M. Haviland-Jones. 4. edition. New York, NY et al. 2016. pp. 3–49. 2744 </li><br><li class="biblio" id="reagan_arcs_2016">Andrew&nbsp;J. Reagan / Lewis Mitchell / Dilan Kiley /
2233 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=857367250" target="_blank">Nachweis im GVK</a>] 2745 Christopher&nbsp;M. Danforth / Peter&nbsp;Sheridan Dodds: The emotional arcs of stories
2234 </li><br><li class="biblio" id="scherer_emotions_2005">Klaus&nbsp;R. Scherer: What are emotions? And how can they be measured? In: Social 2746 are dominated by six basic shapes. In: EPJ Data Science 5 (2016), i. 1, pp.
2235 Science Information 44 (2005), i. 4, pp. 695–729. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129086541" target="_blank">Nachweis im GVK</a>] 2747 31–43. DOI: <a href="https://doi.org/10.1140/epjds/s13688-016-0093-1" target="_blank">10.1140/epjds/s13688-016-0093-1</a></li><br><li class="biblio" id="reed_poetry_2018">Ethan Reed: Measured unrest in the poetry of the
2236 </li><br><li class="biblio" id="schreibman_compainion_2016">Susan Schreibman / Ray Siemens / John Unsworth: A New Companion to Digital 2748 black arts movement. Digital Humanities 2018: Puentes-Bridges. Book of
2237 Humanities. Chichester et al. 2015/2016. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=838374875" target="_blank">Nachweis im GVK</a>] 2749 Abstracts. Hg. von Jonathan Girón Palau / Isabel Galina Russell. (DH 2018,
2238 </li><br><li class="biblio" id="schwarz_emotion_2000">Norbert Schwarz: Emotion, cognition, and decision making. In: Cognition &amp; 2750 Mexico City, 26.–29.06.2018) Mexico City 2018, pp. 477–478. PDF. [<a href="https://dh2018.adho.org/wp-content/uploads/2018/06/dh2018_abstracts.pdf" target="_blank">online</a>]
2239 Emotion 14 (2000), i. 4, pp. 433–440. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=168132915" target="_blank">Nachweis im GVK</a>] 2751 </li><br><li class="biblio" id="reman_corpus_2019">REMAN - Relational Emotion Annotation for
2240 </li><br><li class="biblio" id="smith_models_2009">Herman Smith / Andreas Schneider: Critiquing models of emotions. In: Sociological 2752 Fiction. Relational EMotion ANnotation – a corpus with 1720 fictional text
2241 Methods &amp; Research 37 (2009), i. 4, pp. 560–589. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129299553" target="_blank">Nachweis im GVK</a>] 2753 exceprts from the Project Gutenberg. Ed. by Evgeny Kim / Roman Klinger,
2242 </li><br><li class="biblio" id="soleymani_survey_2017">Mohammad Soleymani / David Garcia / Brendan Jou / Björn Schuller / Shih-Fu Chang / 2754 Universität Stuttgart, Institut für Maschinelle Sprachverarbeitung. In:
2243 Maja Pantic: A survey of multimodal sentiment analysis. In: Image and Vision 2755 ims.uni-stuttgart.de. Institut für Maschinelle Sprachverarbeitung. Forschung.
2244 Computing 65 (2017), pp. 3–14. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129144428" target="_blank">Nachweis im GVK</a>] 2756 Ressourcen Korpora. Stuttgart 2018. [<a href="http://www.ims.uni-stuttgart.de/data/reman" target="_blank">online</a>]
2245 </li><br><li class="biblio" id="sousa_emotion_2018">Ronald de&nbsp;Sousa / Andrea Scarantino: Emotion. In: The Stanford Encyclopedia of 2757 </li><br><li class="biblio" id="richins_emotions_1997">Marsha&nbsp;L. Richins: Measuring emotions in the
2246 Philosophy. Ed. by Edward&nbsp;N. Zalta. Stanford, CA 2018. Article from 25.09.2018. [<a href="https://plato.stanford.edu/archives/win2018/entries/emotion/#Aca" target="_blank">online</a>] 2758 consumption experience. In: Journal of consumer research 24 (1997), i. 2, pp.
2247 </li><br><li class="biblio" id="sprugnoli_analysis_2016">Rachele Sprugnoli / Sara Tonelli / Alessandro Marchetti / Giovanni Moretti: 2759 127–146. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129412023" target="_blank">Nachweis im GVK</a>]
2248 Towards sentiment analysis for historical texts. In: Digital Scholarship in the 2760 </li><br><li class="biblio" id="rinaldi_discoveries_2013">Sergio Rinaldi / Pietro Landi / Fabio
2249 Humanities 31 (2016), i. 4, pp. 762–772. DOI: <a href="https://doi.org/10.1093/llc/fqv027" target="_blank">10.1093/llc/fqv027</a> [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=822236249" target="_blank">Nachweis im GVK</a>] 2761 Della Rossa: Small discoveries can have great consequences in love affairs: the
2250 </li><br><li class="biblio" id="stone_inquirer_19688">Philip&nbsp;J. Stone / Dexter&nbsp;C. Dunphy / Marshall&nbsp;S. Smith: The General Inquirer: A 2762 case of Beauty and the Beast. In: International Journal of Bifurcation and
2251 computer approach to content analysis. In: American Journal of Sociology 73 (1968), 2763 Chaos 23 (2013), i. 11. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=130955957" target="_blank">Nachweis im GVK</a>]
2252 i. 5, pp. 634–635. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129077739" target="_blank">Nachweis im GVK</a>] 2764 </li><br><li class="biblio" id="robinson_reason_2005">Jenefer Robinson: Deeper than reason: Emotion
2253 </li><br><li class="biblio" id="strapparava_extension_2004">Carlo Strapparava / Alessandro Valitutti. WordNet-Affect: An affective extension 2765 and its role in literature, music, and art. New York, NY 2005. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=476217229" target="_blank">Nachweis im GVK</a>]
2254 of WordNet. In: Proceedings of the 4th International Conference on Language Resources 2766 </li><br><li class="biblio" id="ross_encounter_1999">Catherine&nbsp;Sheldrick Ross: Finding without
2255 and Evaluation. Ed. by Maria Teresa Lino / Maria Francisca Xavier / Fátima Ferreira 2767 seeking: the information encounter in the context of reading for pleasure. In:
2256 / 2768 Information Processing &amp; Management 35 (1999), i. 6., pp. 783–799. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129428205" target="_blank">Nachweis im GVK</a>]
2257 Rute Costa / Raquel Silva. 9 volumes. (LREC: 4, Lisbon, 24.-30.05.2004) Paris et al. 2769 </li><br><li class="biblio" id="russell_model_1980">James&nbsp;A. Russell: A circumplex model of affect.
2258 2004. Vol. 4, pp. 1083–1086. PDF. [<a href="http://www.lrec-conf.org/proceedings/lrec2004/pdf/369.pdf" target="_blank">online</a>] 2770 In: Journal of Personality and Social Psychology 39 (1980), pp. 1161–1178. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129078964" target="_blank">Nachweis im GVK</a>]
2259 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=389383694" target="_blank">Nachweis im GVK</a>] 2771 </li><br><li class="biblio" id="russell_recognition_1994">James&nbsp;A. Russell: Is there universal
2260 </li><br><li class="biblio" id="suttles_supervision_2013">Jared Suttles / Nancy Ide: Distant supervision for emotion classification with 2772 recognition of emotion from facial expression? A review of the cross-cultural
2261 discrete binary values. In: Computational Linguistics and Intelligent Text 2773 studies. In: Psychological bulletin 115 (1994), i. 1, pp. 102–141. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129067016" target="_blank">Nachweis im GVK</a>]
2262 Processing. Ed. by Alexander Gelbukh. 2 volumes. (CICLing: 14, Samos, 24.-30.03.2013) 2774 </li><br><li class="biblio" id="russell_affect_2003">James&nbsp;A. Russell: Core affect and the
2263 Berlin et al. 2013. Vol. 2, pp. 121–136. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=744907373" target="_blank">Nachweis im GVK</a>] 2775 psychological construction of emotion. In: Psychological review 110 (2003), i.
2264 </li><br><li class="biblio" id="taboada_classification_2006">Maite Taboada / Mary&nbsp;Ann Gillies / Paul McFetridge: Sentiment classification 2776 1, pp. 145–172. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129509493" target="_blank">Nachweis im GVK</a>]
2265 techniques for tracking literary reputation. In: LREC workshop: Towards computational 2777 </li><br><li class="biblio" id="russell_affect_1999">James&nbsp;A. Russell / Lisa&nbsp;Feldman Barrett: Core
2266 models of literary analysis. (LREC: 5, Genoa, 22.-28.05.2006) , pp. 36–43. Paris 2778 affect, prototypical emotional episodes, and other things called emotion:
2267 2006. [<a href="http://www.lrec-conf.org/proceedings/lrec2006/workshops/W04/Literary%20analysis.pdf" target="_blank">online</a>] 2779 dissecting the elephant. In: Journal of Personality and Social Psychology 76
2268 </li><br><li class="biblio" id="taboada_reputation_2008">Maite Taboada / Mary&nbsp;Ann Gillies / Paul McFetridge / Robert Outtrim: Tracking 2780 (1999), i. 5, pp. 805–819. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129078964" target="_blank">Nachweis im GVK</a>]
2269 literary reputation with text analysis tools. In: Meeting of the Society for Digital 2781 </li><br><li class="biblio" id="russell_expressions_2003">James&nbsp;A. Russell / Jo-Anne Bachorowski /
2270 Humanities. Vancouver 2008. PDF. [<a href="http://www.sfu.ca/~mtaboada/docs/publications/Taboada_et_al_SDH_2008.pdf" target="_blank">online</a>] 2782 José-Miguel Fernández-Dols: Facial and vocal expressions of emotion. In: Annual
2271 </li><br><li class="biblio" id="tolstoy_art_1962">Leo Tolstoy: What is art? And essays on art. Harmondsworth 1962. (= Penguin 2783 review of psychology 54 (2003), i. 1, pp. 329–349. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129499366" target="_blank">Nachweis im GVK</a>]
2272 classics) Siehe auch [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=21799721X" target="_blank">Nachweis im GVK</a>] 2784 </li><br><li class="biblio" id="saetre_exploring_2014">Exploring Text and Emotions. Ed. by Lars
2273 </li><br><li class="biblio" id="tomkins_consciousness_1962">Silvan Tomkins: Affect imagery consciousness. 4 vol. New York, NY et al. 1962. 2785 Sætre / Patrizia Lombardo / Julien Zanetta (2014a). Aarhus 2014. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=782781934" target="_blank">Nachweis im GVK</a>]
2274 Vol. I: The positive affects. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=037368567" target="_blank">Nachweis im GVK</a>] 2786 </li><br><li class="biblio" id="saetre_text_2014">Lars Sætre / Patrizia Lombardo / Julien Zanetta
2275 </li><br><li class="biblio" id="vanhorn_characters_1997">Leigh Van&nbsp;Horn: The characters within us: Readers connect with characters to 2787 (2014b): Text and Emotions. In: Exploring Text and Emotions. Ed. by Lars Sætre
2276 create meaning and understanding. In: Journal of Adolescent &amp; Adult Literacy 40 2788 / Patrizia Lombardo / Julien Zanetta. Aarhus 2014, pp. 9–26. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=782781934" target="_blank">Nachweis im GVK</a>]
2277 (1997), i. 5, pp. 342–347. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=19105335X" target="_blank">Nachweis im GVK</a>] 2789 </li><br><li class="biblio" id="samothrakis_annotation_2015">Spyridon Samothrakis / Maria Fasli:
2278 </li><br><li class="biblio" id="vanhoutte_gates_2013">Edward Vanhoutte: The gates of hell: History and definition of 2790 Emotional sentence annotation helps predict fiction genre. In: PLOS ONE 10
2279 digital|humanities|computing. In: Defining Digital Humanities. A Reader. Ed. by 2791 (2015), i. 11, p. e0141922. Article from 02.11.2015. DOI: <a href="https://doi.org/10.1371/journal.pone.0141922" target="_blank">10.1371/journal.pone.0141922</a></li><br><li class="biblio" id="samur_session_2018">Dalya Samur / Mattie Tops / Sander&nbsp;L. Koole:
2280 Meliss Terras / Julianne Hyhan / Edward Vanhoutte. Farnham 2013, pp. 119–156. 2792 Does a single session of reading literary fiction prime enhanced mentalising
2281 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=766493245" target="_blank">Nachweis im GVK</a>] 2793 performance? Four replication experiments of Kidd and Castano (2013). In:
2282 </li><br><li class="biblio" id="vonnegut_blackboard_2010">Kurt Vonnegut: Kurt Vonnegut at the Blackboard. Ed. by Seven Stories Press. New York, 2794 Cognition &amp; Emotion 32 (2018), pp. 130–144. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=168132915" target="_blank">Nachweis im GVK</a>]
2283 NY 2005. 2795 </li><br><li class="biblio" id="scarantino_philosophy_2016">Andrea Scarantino: The Philosophy of
2284 In: Lapham’s Quarterly (2010). Article from 26.03.2010. [<a href="https://www.laphamsquarterly.org/arts-letters/blackboard" target="_blank">online</a>] 2796 Emotions and Its Impact on Affective Sciences. In: Handbook of emotions. Ed. by
2285 </li><br><li class="biblio" id="yu_evaluation_2008">Bei Yu: An evaluation of text classification methods for literary study. In: 2797 Lisa Feldman Barret / Michael Lewis / Jeannette M. Haviland-Jones. 4. edition.
2286 Literary and Linguistic Computing 23 (2008), i. 3, pp. 327–343. DOI: <a href="https://doi.org/10.1093/llc/fqn015" target="_blank">10.1093/llc/fqn015</a></li><br><li class="biblio" id="zehe_prediction_2016">Albin Zehe / Martin Becker / Lena Hettinger / Andreas Hotho / Isabella Reger / 2798 New York, NY et al. 2016. pp. 3–49. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=857367250" target="_blank">Nachweis im GVK</a>]
2287 Fotis Jannidis: Prediction of happy endings in German novels based on sentiment 2799 </li><br><li class="biblio" id="scherer_emotions_2005">Klaus&nbsp;R. Scherer: What are emotions? And how
2288 information. In: Proceedings of the Workshop on Interactions between Data Mining and 2800 can they be measured? In: Social Science Information 44 (2005), i. 4, pp.
2289 Natural Language Processing 2016. Ed. by Peggy Cellier / Thierry Charnois / Andreas 2801 695–729. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129086541" target="_blank">Nachweis im GVK</a>]
2290 Hotho / Stan Matwin / Marie-Francine Moens&nbsp;/ Yannick Toussaint. (DMNLP: 3, Riva del 2802 </li><br><li class="biblio" id="schmidt_evaluation_2018">Thomas Schmidt / Manuel Burghardt: An Evaluation of Lexicon-based
2291 Garda, 19.-23.09.2016) Aachen 2016, pp.&nbsp;9–16. URN: <a href="http://nbn-resolving.de/urn:nbn:de:0074-1646-4" target="_blank">urn:nbn:de:0074-1646-4</a></li><br><li class="biblio" id="zhuravlev_affairs_2014">Mikhail Zhuravlev / Irina Golovacheva / Polina de&nbsp;Mauny: Mathematical modelling of 2803 Sentiment Analysis Techniques for the Plays of Gotthold Ephraim Lessing.
2292 love affairs between the characters of the pre-masochistic novel. In: 2014 Second 2804 In: Proceedings of the Second Joint SIGHUM Workshop on Computational
2293 World Conference on Complex Systems (WCCS: 2, Adagir, 10.-12.11.2014) Piscataway, 2805 Linguistics for Cultural Heritage, Social Sciences, Humanities and
2294 NJ 2014, 2806 Literature. Stroudsburg, PA 2018, pp. 139–149. [<a href="https://www.aclweb.org/anthology/W18-4516" target="_blank">online</a>]
2295 pp. 396–401. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=835708772" target="_blank">Nachweis im GVK</a>] 2807 </li><br><li class="biblio" id="schreibman_compainion_2016">Susan Schreibman / Ray Siemens / John
2296 </li><br><li class="biblio" id="zillmann_effect_1980">Dolf Zillmann / Richard&nbsp;T. Hezel / Norman&nbsp;J. Medoff: The effect of affective 2808 Unsworth: A New Companion to Digital Humanities. Chichester et al. 2015/2016.
2297 states on selective exposure to televised entertainment fare. In: Journal of Applied 2809 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=838374875" target="_blank">Nachweis im GVK</a>]
2298 Social Psychology 10 (1980), i. 4, pp. 323–339. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129288942" target="_blank">Nachweis im GVK</a>] 2810 </li><br><li class="biblio" id="schwarz_emotion_2000">Norbert Schwarz: Emotion, cognition, and
2811 decision making. In: Cognition &amp; Emotion 14 (2000), i. 4, pp. 433–440. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=168132915" target="_blank">Nachweis im GVK</a>]
2812 </li><br><li class="biblio" id="shaikh_interpretation_2009">Mostafa&nbsp;Al&nbsp;Masum&nbsp;Shaikh / Helmut&nbsp;Prendinger / Mitsuru&nbsp;Ishizuka: A
2813 Linguistic Interpretation of the OCC Emotion Model for Affect Sensing
2814 from Text. In: Affective Information Processing. Ed. by Jianhua Tao / Tieniu Tan.
2815 London 2009. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=562088369" target="_blank">Nachweis im GVK</a>]
2816 </li><br><li class="biblio" id="smith_patterns_1985">Craig. A. Smith / Phoebe C. Ellsworth: Patterns of cognitive
2817 appraisal in emotion. Journal of Personality and Social Psychology 48
2818 (1985), pp. 813–838. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129078964" target="_blank">Nachweis im GVK</a>]
2819 </li><br><li class="biblio" id="smith_models_2009">Herman Smith / Andreas Schneider: Critiquing
2820 models of emotions. In: Sociological Methods &amp; Research 37 (2009), i. 4,
2821 pp. 560–589. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129299553" target="_blank">Nachweis im GVK</a>]
2822 </li><br><li class="biblio" id="soleymani_survey_2017">Mohammad Soleymani / David Garcia / Brendan
2823 Jou / Björn Schuller / Shih-Fu Chang / Maja Pantic: A survey of multimodal
2824 sentiment analysis. In: Image and Vision Computing 65 (2017), pp. 3–14. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129144428" target="_blank">Nachweis im GVK</a>]
2825 </li><br><li class="biblio" id="sousa_emotion_2018">Ronald de&nbsp;Sousa / Andrea Scarantino: Emotion.
2826 In: The Stanford Encyclopedia of Philosophy. Ed. by Edward&nbsp;N. Zalta. Stanford,
2827 CA 2018. Article from 25.09.2018. [<a href="https://plato.stanford.edu/archives/win2018/entries/emotion/#Aca" target="_blank">online</a>]
2828 </li><br><li class="biblio" id="sprugnoli_analysis_2016">Rachele Sprugnoli / Sara Tonelli /
2829 Alessandro Marchetti / Giovanni Moretti: Towards sentiment analysis for
2830 historical texts. In: Digital Scholarship in the Humanities 31 (2016), i. 4,
2831 pp. 762–772. DOI: <a href="https://doi.org/10.1093/llc/fqv027" target="_blank">10.1093/llc/fqv027</a> [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=822236249" target="_blank">Nachweis im GVK</a>]
2832 </li><br><li class="biblio" id="stone_inquirer_19688">Philip&nbsp;J. Stone / Dexter&nbsp;C. Dunphy /
2833 Marshall&nbsp;S. Smith: The General Inquirer: A computer approach to content
2834 analysis. In: American Journal of Sociology 73 (1968), i. 5, pp. 634–635. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129077739" target="_blank">Nachweis im GVK</a>]
2835 </li><br><li class="biblio" id="strapparava_extension_2004">Carlo Strapparava / Alessandro
2836 Valitutti. WordNet-Affect: An affective extension of WordNet. In: Proceedings
2837 of the 4th International Conference on Language Resources and Evaluation. Ed.
2838 by Maria Teresa Lino / Maria Francisca Xavier / Fátima Ferreira / Rute Costa /
2839 Raquel Silva. 9 volumes. (LREC: 4, Lisbon, 24.–30.05.2004) Paris et al. 2004.
2840 Vol. 4, pp. 1083–1086. PDF. [<a href="http://www.lrec-conf.org/proceedings/lrec2004/pdf/369.pdf" target="_blank">online</a>] [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=389383694" target="_blank">Nachweis im GVK</a>]
2841 </li><br><li class="biblio" id="suttles_supervision_2013">Jared Suttles / Nancy Ide: Distant
2842 supervision for emotion classification with discrete binary values. In:
2843 Computational Linguistics and Intelligent Text Processing. Ed. by Alexander
2844 Gelbukh. 2 volumes. (CICLing: 14, Samos, 24.–30.03.2013) Berlin et al. 2013.
2845 Vol. 2, pp. 121–136. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=744907373" target="_blank">Nachweis im GVK</a>]
2846 </li><br><li class="biblio" id="taboada_classification_2006">Maite Taboada / Mary&nbsp;Ann Gillies / Paul
2847 McFetridge: Sentiment classification techniques for tracking literary
2848 reputation. In: LREC workshop: Towards computational models of literary
2849 analysis. (LREC: 5, Genoa, 22.-28.05.2006) , pp. 36–43. Paris 2006. [<a href="http://www.lrec-conf.org/proceedings/lrec2006/workshops/W04/Literary%20analysis.pdf" target="_blank">online</a>]
2850 </li><br><li class="biblio" id="taboada_reputation_2008">Maite Taboada / Mary&nbsp;Ann Gillies / Paul
2851 McFetridge / Robert Outtrim: Tracking literary reputation with text analysis
2852 tools. In: Meeting of the Society for Digital Humanities. Vancouver 2008. PDF.
2853 [<a href="http://www.sfu.ca/~mtaboada/docs/publications/Taboada_et_al_SDH_2008.pdf" target="_blank">online</a>]
2854 </li><br><li class="biblio" id="tolstoy_art_1962">Leo Tolstoy: What is art? And essays on art.
2855 Harmondsworth 1962. (= Penguin classics) Siehe auch [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=21799721X" target="_blank">Nachweis im GVK</a>]
2856 </li><br><li class="biblio" id="tomkins_consciousness_1962">Silvan Tomkins: Affect imagery
2857 consciousness. 4 vol. New York, NY et al. 1962. Vol. I: The positive affects.
2858 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=037368567" target="_blank">Nachweis im GVK</a>]
2859 </li><br><li class="biblio" id="vanhorn_characters_1997">Leigh Van&nbsp;Horn: The characters within us:
2860 Readers connect with characters to create meaning and understanding. In:
2861 Journal of Adolescent &amp; Adult Literacy 40 (1997), i. 5, pp. 342–347. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=19105335X" target="_blank">Nachweis im GVK</a>]
2862 </li><br><li class="biblio" id="volkova_perception_2010">Ekaterina P. Volkova / Betty Mohler / Detmar Meurers / Dale Gerdemann
2863 / Heinrich H. Bülthoff: Emotional perception of fairy tales: achieving
2864 agreement in emotion annota-tion of text. In Proceedings of the NAACL
2865 HLT 2010 Workshop on Computational Ap-proaches to Analysis and
2866 Generation of Emotion in Text (2010), pp. 98–106. [<a href="https://www.aclweb.org/anthology/W10-0212" target="_blank">online</a>]
2867 </li><br><li class="biblio" id="vanhoutte_gates_2013">Edward Vanhoutte: The gates of hell: History
2868 and definition of digital|humanities|computing. In: Defining Digital
2869 Humanities. A Reader. Ed. by Meliss Terras / Julianne Hyhan / Edward Vanhoutte.
2870 Farnham 2013, pp. 119–156. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=766493245" target="_blank">Nachweis im GVK</a>]
2871 </li><br><li class="biblio" id="vonnegut_blackboard_2010">Kurt Vonnegut: Kurt Vonnegut at the
2872 Blackboard. Ed. by Seven Stories Press. New York, NY 2005. In: Lapham’s
2873 Quarterly (2010). Article from 26.03.2010. [<a href="https://www.laphamsquarterly.org/arts-letters/blackboard" target="_blank">online</a>]
2874 </li><br><li class="biblio" id="wiebe_language_2004">Janyce Wiebe / Theresa Wilson / Rebecca Bruce / Matthew Bell / Melanie
2875 Martin: Learning Subjective Language. In: Computational Linguistics 30
2876 (2004), pp. 277–308. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=130396419" target="_blank">Nachweis im GVK</a>]
2877 </li><br><li class="biblio" id="yu_evaluation_2008">Bei Yu: An evaluation of text classification
2878 methods for literary study. In: Literary and Linguistic Computing 23 (2008), i.
2879 3, pp. 327–343. DOI: <a href="https://doi.org/10.1093/llc/fqn015" target="_blank">10.1093/llc/fqn015</a></li><br><li class="biblio" id="zehe_prediction_2016">Albin Zehe / Martin Becker / Lena Hettinger /
2880 Andreas Hotho / Isabella Reger / Fotis Jannidis: Prediction of happy endings in
2881 German novels based on sentiment information. In: Proceedings of the Workshop
2882 on Interactions between Data Mining and Natural Language Processing 2016. Ed.
2883 by Peggy Cellier / Thierry Charnois / Andreas Hotho / Stan Matwin /
2884 Marie-Francine Moens&nbsp;/ Yannick Toussaint. (DMNLP: 3, Riva del Garda,
2885 19.–23.09.2016) Aachen 2016, pp.&nbsp;9–16. URN: <a href="http://nbn-resolving.de/urn:nbn:de:0074-1646-4" target="_blank">urn:nbn:de:0074-1646-4</a></li><br><li class="biblio" id="zhuravlev_affairs_2014">Mikhail Zhuravlev / Irina Golovacheva /
2886 Polina de&nbsp;Mauny: Mathematical modelling of love affairs between the characters
2887 of the pre-masochistic novel. In: 2014 Second World Conference on Complex
2888 Systems (WCCS: 2, Adagir, 10.–12.11.2014) Piscataway, NJ 2014, pp. 396–401.
2889 [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=835708772" target="_blank">Nachweis im GVK</a>]
2890 </li><br><li class="biblio" id="zillmann_effect_1980">Dolf Zillmann / Richard&nbsp;T. Hezel / Norman&nbsp;J.
2891 Medoff: The effect of affective states on selective exposure to televised
2892 entertainment fare. In: Journal of Applied Social Psychology 10 (1980), i. 4,
2893 pp. 323–339. [<a href="https://kxp.k10plus.de/DB=2.1/PPN?PPN=129288942" target="_blank">Nachweis im GVK</a>]
2299 </li><br></ul> 2894 </li><br></ul>
2300 </div> 2895 </div>
2896 </div>
2301 <div class="abbildungsnachweis"> 2897 <div class="abbildungsnachweis">
2302 <hr><a name="hd28"> </a><h2> 2898 <hr><a name="div32"> </a><div id="abbildungsnachweis"><a name="hd30"> </a><h2>
2303 <div style="position:relative;width:90%;">List of Figures with Captions</div> 2899 <div style="position:relative;width:90%;">List of Figures with Captions</div>
2305 <ul class="abbildung"> 2901 <ul class="abbildung">
2306 <li id="abb1"><a href="#emotion_analysis_2019_001">Fig. 1</a>: Plutchik’s wheel of emotions. [<a href="#plutchik_wheel_2011">Plutchik 2011</a>. 2902 <li id="abb1"><a href="#emotion_analysis_2019_001">Fig. 1</a>: Plutchik’s wheel of emotions. [<a href="#plutchik_wheel_2011">Plutchik 2011</a>. <a href="https://creativecommons.org/publicdomain/mark/1.0/deed.de">PD</a>]<a href="#emotion_analysis_2019_001"></a></li>
2307 <a href="https://creativecommons.org/publicdomain/mark/1.0/deed.de">PD</a>]<a href="#emotion_analysis_2019_001"></a></li>
2308 </ul> 2903 </ul>
2309 <ul class="abbildung"> 2904 <ul class="abbildung">
2310 <li id="abb2"><a href="#emotion_analysis_2019_002">Fig. 2</a>: Circumplex model of affect: Horizontal axis represents the valence dimension, 2905 <li id="abb2"><a href="#emotion_analysis_2019_002">Fig. 2</a>: Circumplex model of affect: Horizontal axis
2311 the vertical axis represents the arousal dimension. Drawn after <a href="#posner_model_2005">Posner et al. 2005</a>. [Kim / Klinger 2019]<a href="#emotion_analysis_2019_002"></a></li> 2906 represents the valence dimension, the vertical axis represents the arousal
2907 dimension. Drawn after <a href="#posner_model_2005">Posner
2908 et al. 2005</a>. [Kim / Klinger 2019]<a href="#emotion_analysis_2019_002"></a></li>
2312 </ul> 2909 </ul>
2313 <ul class="abbildung"> 2910 <ul class="abbildung">
2314 <li id="abb3"><a href="#emotion_analysis_2019_003">Tab. 3</a>: Summary of characteristics of methods used in the papers reviewed 2911 <li id="abb3"><a href="#emotion_analysis_2019_003">Tab. 1</a>: Summary of characteristics of methods used in the
2315 in this survey. Download as <a href="http://www.zfdg.de/files/table_zfdg_klinger.pdf">PDF</a>. [Kim / Klinger 2019]<a href="#emotion_analysis_2019_003"></a></li> 2912 papers reviewed in this survey. Download as <a href="http://www.zfdg.de/files/table_zfdg_klinger.pdf">PDF</a>. [Kim /
2913 Klinger 2021]<a href="#emotion_analysis_2019_003"></a></li>
2316 </ul> 2914 </ul>
2317 </div>2915 </div>
2916 </div>
2917 </body>
2918
2919