Ahmad Affective Computing and Sentiment Analysis

Emotion, Metaphor and Terminology
1. Auflage 2011
ISBN: 978-94-007-1757-2
Verlag: Springer Netherlands
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, Band 45, 158 Seiten

Reihe: Text, Speech and Language Technology

This volume maps the watershed areas between two 'holy grails' of computer science: the identification and interpretation of affect - including sentiment and mood. The expression of sentiment and mood involves the use of metaphors, especially in emotive situations. Affect computing is rooted in hermeneutics, philosophy, political science and sociology, and is now a key area of research in computer science. The 24/7 news sites and blogs facilitate the expression and shaping of opinion locally and globally.  Sentiment analysis, based on text and data mining, is being used in the looking at news and blogs for purposes as diverse as: brand management, film reviews, financial market analysis and prediction, homeland security. There are systems that learn how sentiments are articulated. This work draws on, and informs, research in fields as varied as artificial intelligence, especially reasoning and machine learning, corpus-based information extraction, linguistics, and psychology. 

Autoren/Hrsg.

Ahmad, Khurshid

Inhaltsverzeichnis

1;Acknowledgments;6
2;Introduction: Affect Computing and SentimentAnalysis;7
2.1;References;10
3;Contents;11
4;Contributors;13
5;1 Understanding Metaphors: The Paradox of Unlike Things Compared;15
5.1;1.1 Introduction;15
5.2;1.2 The Metaphor Paraphrase Problem and the Priority of the Literal;16
5.3;1.3 Understanding Metaphors: Comparison or Categorization?;17
5.4;1.4 How Novel Categories Can Be Named: Dual Reference;18
5.5;1.5 Understanding Metaphors and Similes;20
5.6;1.6 The Metaphor Paraphrase Problem Revisited;22
5.7;1.7 Comparison Versus Categorization Revisited;23
5.8;1.8 Conclusions;24
5.9;References;25
6;2 Metaphor as Resource for the Conceptualisation and Expression of Emotion;27
6.1;2.1 Background;27
6.2;2.2 Metaphorical Conceptualisation of Emotions in English;28
6.2.1;2.2.1 Conceptualisation of Emotion;28
6.2.2;2.2.2 Description and Expression of Emotion;30
6.3;2.3 Contribution of English Metaphor Themes to the Expression of Emotion;31
6.3.1;2.3.1 Metalude Data for Evaluation;31
6.3.2;2.3.2 Evaluative Transfer;32
6.3.3;2.3.3 Evaluation Dependent on Larger Schemata;34
6.3.4;2.3.4 Ideology and Evaluation;35
6.3.5;2.3.5 The Role of Multivalency and Opposition in Metaphor Themes;37
6.4;2.4 Conclusion;39
6.5;References;39
7;3 The Deep Lexical Semantics of Emotions;40
7.1;3.1 Introduction;40
7.2;3.2 Identifying the Core Emotion Words;41
7.3;3.3 Filling Out the Lexicon of Emotion;41
7.4;3.4 Some Core Theories;43
7.5;3.5 The Theory and Lexical Semantics of Emotion;44
7.6;3.6 Summary;46
7.7;References;47
8;4 Genericity and Metaphoricity Both Involve Sense Modulation;48
8.1;4.1 Background;48
8.2;4.2 Dynamics of First-Order Information;51
8.2.1;4.2.1 Some Intuitions About Revision;51
8.2.2;4.2.2 A Formal Model of First-Order Belief Revision;52
8.2.3;4.2.3 First-Order Belief Revision Adapted to Sense Extension;53
8.3;4.3 Ramifications for Metaphoricity;55
8.4;4.4 Metaphoricity and Genericity;57
8.5;4.5 Particulars of the Class-Inclusion Framework;60
8.6;4.6 Final Remarks;63
8.7;References;63
9;5 Affect Transfer by Metaphor for an Intelligent Conversational Agent;65
9.1;5.1 Introduction;65
9.2;5.2 Affect via Metaphor in an ICA;67
9.3;5.3 Metaphor Processing;68
9.3.1;5.3.1 The Recognition Component;68
9.3.2;5.3.2 The Analysis Component;70
9.4;5.4 Examples of the Course of Processing;73
9.4.1;5.4.1 You Piglet;73
9.4.2;5.4.2 Lisa Is an Angel;74
9.4.3;5.4.3 Mayid Is a Rock;74
9.4.4;5.4.4 Other Examples;74
9.5;5.5 Results;75
9.6;5.6 Conclusions and Further Work;76
9.7;References;77
10;6 Detecting Uncertainty in Spoken Dialogues: An Exploratory Research for the Automatic Detection of Speaker Uncertainty by Using Prosodic Markers;79
10.1;6.1 Introduction;79
10.2;6.2 Related Work;79
10.2.1;6.2.1 Defining (Un)certainty;79
10.2.2;6.2.2 Linguistic Pointers to Uncertainty;81
10.2.3;6.2.3 Prosodic Markers of Uncertainty;81
10.3;6.3 Problem Statement;82
10.4;6.4 Data Selection;83
10.4.1;6.4.1 Selection of Meetings;83
10.4.2;6.4.2 Data Preparation and Selection;83
10.4.3;6.4.3 Statistical Analysis;84
10.5;6.5 Experimentation;85
10.5.1;6.5.1 Hedges --vs-- No Hedges;85
10.5.2;6.5.2 Uncertain Hedges --vs-- Certain Hedges;86
10.5.3;6.5.3 Distribution of Hedges Over Dialogue Acts;88
10.6;6.6 Conclusions;88
10.7;References;89
11;7 Metaphors and Metaphor-Like Processes Across Languages: Notes on English and Italian Language of Economics;90
11.1;7.1 Introduction;90
11.2;7.2 Corpus and Method;92
11.2.1;7.2.1 Corpus;92
11.2.2;7.2.2 Method;92
11.3;7.3 Analysis;93
11.3.1;7.3.1 Constitutive Metaphors;93
11.3.2;7.3.2 Pedagogic Metaphors;96
11.3.3;7.3.3 Universal vs. Culture-Specific Metaphors;96
11.4;7.4 Conclusion;97
11.5;References;98
12;8 The `Return' and `Volatility' of Sentiments: An Attempt to Quantify the Behaviour of the Markets?;100
12.1;8.1 Introduction;100
12.2;8.2 Metaphors of `Return' and of `Volatility';100
12.3;8.3 The Roots of Computational Sentiment Analysis;103
12.4;8.4 A Corpus-Based Study of Sentiments, Terminology and Ontology Over Time;104
12.4.1;8.4.1 Corpus Preparation and Composition;105
12.4.2;8.4.2 Candidate Terminology and Ontology;105
12.4.3;8.4.3 Historical Volatility in Our Corpus;106
12.5;8.5 Afterword;108
12.6;References;109
13;9 Sentiment Analysis Using Automatically Labelled Financial News Items;111
13.1;9.1 Introduction;111
13.2;9.2 Data and Method;112
13.2.1;9.2.1 Training and Testing Corpus;112
13.2.2;9.2.2 Feature Types;112
13.2.3;9.2.3 Feature Selection and Counting Methods;113
13.2.4;9.2.4 News Items and Stock Price Correlation;114
13.2.5;9.2.5 Feature Selection and Semantic Relatedness of Documents;115
13.3;9.3 Results;116
13.3.1;9.3.1 Horizon Effect;116
13.3.2;9.3.2 Polarity Effect;117
13.3.3;9.3.3 Range Effect;118
13.3.4;9.3.4 Effect of Adding a Neutral Class on Non-cotemporaneous Prices: One- and Two-Days Ahead;118
13.3.5;9.3.5 Conflating Two Classes;119
13.3.6;9.3.6 Positive and Negative Features;120
13.4;9.4 Discussion;121
13.4.1;9.4.1 Lack of Independent Testing Corpus;121
13.4.2;9.4.2 Pool of Features;122
13.4.3;9.4.3 Size of Documents;122
13.4.4;9.4.4 Trading Costs;122
13.5;9.5 Conclusion and Future Work;122
13.6;References;123
14;10 Co-Word Analysis for Assessing Consumer Associations: A Case Study in Market Research;125
14.1;10.1 Introduction;125
14.2;10.2 Conceptual Background;126
14.2.1;10.2.1 Consumer Associations and Mental Processing;126
14.2.2;10.2.2 Drawbacks of Manual Data Analysis;127
14.2.3;10.2.3 Requirements for Automated Co-Word Analysis;127
14.3;10.3 Technique and Implementation;128
14.3.1;10.3.1 Import of Text Sources;129
14.3.2;10.3.2 Processing of Text;129
14.3.3;10.3.3 Graph Creation and Clustering;129
14.4;10.4 Exemplary Case Study;130
14.5;10.5 Conclusion and Outlook;132
14.6;References;133
15;11 Automating Opinion Analysis in Film Reviews: The Case of Statistic Versus Linguistic Approach;135
15.1;11.1 Introduction;135
15.2;11.2 Related Work;136
15.2.1;11.2.1 Machine Learning for Opinion Analysis;136
15.2.2;11.2.2 Linguistic Methods of Opinion Analysis;137
15.3;11.3 Linguistic and Machine Learning Methods: A Comparative Study;140
15.3.1;11.3.1 Linguistic Approach;140
15.3.2;11.3.2 Machine Learning Approach;143
15.4;11.4 Conclusion and Prospects;147
15.5;References;148
16;Afterword: `The Fire Sermon';151
17;Name Index;155
18;Subject Index;157