Details

Automatic Detection of Irony


Automatic Detection of Irony

Opinion Mining in Microblogs and Social Media
1. Aufl.

von: Jihen Karoui, Farah Benamara, Veronique Moriceau

139,99 €

Verlag: Wiley
Format: EPUB
Veröffentl.: 28.10.2019
ISBN/EAN: 9781119671220
Sprache: englisch
Anzahl Seiten: 210

DRM-geschütztes eBook, Sie benötigen z.B. Adobe Digital Editions und eine Adobe ID zum Lesen.

Beschreibungen

In recent years, there has been a proliferation of opinion-heavy texts on the Web: opinions of Internet users, comments on social networks, etc. Automating the synthesis of opinions has become crucial to gaining an overview on a given topic. Current automatic systems perform well on classifying the subjective or objective character of a document. However, classifications obtained from polarity analysis remain inconclusive, due to the algorithms' inability to understand the subtleties of human language. Automatic Detection of Irony presents, in three stages, a supervised learning approach to predicting whether a tweet is ironic or not. The book begins by analyzing some everyday examples of irony and presenting a reference corpus. It then develops an automatic irony detection model for French tweets that exploits semantic traits and extralinguistic context. Finally, it presents a study of portability in a multilingual framework (Italian, English, Arabic).
<p>Preface ix</p> <p>Introduction xi</p> <p><b>Chapter 1. From Opinion Analysis to Figurative Language Treatment </b><b>1</b></p> <p>1.1. Introduction 1</p> <p>1.2. Defining the notion of opinion 3</p> <p>1.2.1. The many faces of opinion 3</p> <p>1.2.2. Opinion as a structured model 4</p> <p>1.2.3. Opinion extraction: principal approaches 5</p> <p>1.3. Limitations of opinion analysis systems 7</p> <p>1.3.1. Opinion operators 8</p> <p>1.3.2. Domain dependency 9</p> <p>1.3.3. Implicit opinions 10</p> <p>1.3.4. Opinions and discursive context above phrase level 11</p> <p>1.3.5. Presence of figurative expressions 12</p> <p>1.4. Definition of figurative language 13</p> <p>1.4.1. Irony 13</p> <p>1.4.2. Sarcasm 18</p> <p>1.4.3. Satire 20</p> <p>1.4.4. Metaphor 21</p> <p>1.4.5. Humor 22</p> <p>1.5. Figurative language: a challenge for NLP 23</p> <p>1.6. Conclusion 23</p> <p><b>Chapter 2. Toward Automatic Detection of Figurative Language </b><b>25</b></p> <p>2.1. Introduction 25</p> <p>2.2. The main corpora used for figurative language 27</p> <p>2.2.1. Corpora annotated for irony/sarcasm 28</p> <p>2.2.2. Corpus annotated for metaphors 33</p> <p>2.3. Automatic detection of irony, sarcasm and satire 36</p> <p>2.3.1. Surface and semantic approaches 36</p> <p>2.3.2. Pragmatic approaches 39</p> <p>2.4. Automatic detection of metaphor 51</p> <p>2.4.1. Surface and semantic approaches 52</p> <p>2.4.2. Pragmatic approaches 53</p> <p>2.5. Automatic detection of comparison 58</p> <p>2.6. Automatic detection of humor 58</p> <p>2.7. Conclusion 61</p> <p><b>Chapter 3. A Multilevel Scheme for Irony Annotation in Social Network Content </b><b>63</b></p> <p>3.1. Introduction 63</p> <p>3.2. The FrIC 65</p> <p>3.3. Multilevel annotation scheme 66</p> <p>3.3.1. Methodology 66</p> <p>3.3.2. Annotation scheme 69</p> <p>3.4. The annotation campaign 79</p> <p>3.4.1. Glozz 79</p> <p>3.4.2. Data preparation 80</p> <p>3.4.3. Annotation procedure 81</p> <p>3.5. Results of the annotation campaign 83</p> <p>3.5.1. Qualitative results 83</p> <p>3.5.2. Quantitative results 84</p> <p>3.5.3. Correlation between different levels of the annotation scheme 89</p> <p>3.6. Conclusion 93</p> <p><b>Chapter 4. Three Models for Automatic Irony Detection </b><b>95</b></p> <p>4.1. Introduction 95</p> <p>4.2. The FrIC<i><sup>Auto</sup></i> corpus 97</p> <p>4.3. The SurfSystem model: irony detection based on surface features 99</p> <p>4.3.1. Selected features 99</p> <p>4.3.2. Experiments and results 101</p> <p>4.4. The PragSystem model: irony detection based on internal contextual features 104</p> <p>4.4.1. Selected features 104</p> <p>4.4.2. Experiments and results 109</p> <p>4.4.3. Discussion 116</p> <p>4.5. The QuerySystem model: developing a pragmatic contextual approach for automatic irony detection 118</p> <p>4.5.1. Proposed approach 118</p> <p>4.5.2. Experiments and results 122</p> <p>4.5.3. Evaluation of the query-based method 123</p> <p>4.6. Conclusion 124</p> <p><b>Chapter 5. Towards a Multilingual System for Automatic Irony Detection </b><b>127</b></p> <p>5.1. Introduction 127</p> <p>5.2. Irony in Indo-European languages 128</p> <p>5.2.1. Corpora 128</p> <p>5.2.2. Results of the annotation process 130</p> <p>5.2.3. Summary 139</p> <p>5.3. Irony in Semitic languages 140</p> <p>5.3.1. Specificities of Arabic 142</p> <p>5.3.2. Corpus and resources 143</p> <p>5.3.3. Automatic detection of irony in Arabic tweets 146</p> <p>5.4. Conclusion 149</p> <p>Conclusion 151</p> <p>Appendix 155</p> <p>References 169</p> <p>Index 189</p>
Jihen Karoui is Research and Development Project Manager at AUSY, France. Farah Benamara is a Senior Lecturer at Paul Sabatier University in Toulouse, France. Veronique Moriceau is a Senior Lecturer at Paul Sabatier University.

Diese Produkte könnten Sie auch interessieren:

Pulsed Power
Pulsed Power
von: Gennady A. Mesyats
PDF ebook
309,23 €
High-Frequency Oscillator Design for Integrated Transceivers
High-Frequency Oscillator Design for Integrated Transceivers
von: J. van der Tang, Dieter Kasperkovitz, Arthur H.M. van Roermund
PDF ebook
149,79 €
MEMS Vibratory Gyroscopes
MEMS Vibratory Gyroscopes
von: Cenk Acar, Andrei Shkel
PDF ebook
149,79 €