Human Language Technology (HLT) and Natural Language Processing (NLP) systems have typically focused on the "factual" aspect of content analysis. Other aspects, including pragmatics, opinion, and style, have received much less attention. However, to achieve an adequate understanding of a text, these aspects cannot be ignored. The chapters in this book address the aspect of subjective opinion, which includes identifying different points of view, identifying different emotive dimensions, and classifying text by opinion. Various conceptual models and computational methods are presented. The models explored in this book include the following: distinguishing attitudes from simple factual assertions; distinguishing between the author's reports from reports of other people's opinions; and distinguishing between explicitly and implicitly stated attitudes. In addition, many applications are described that promise to benefit from the ability to understand attitudes and affect, including indexing and retrieval of documents by opinion; automatic question answering about opinions; analysis of sentiment in the media and in discussion groups about consumer products, political issues, etc.; brand and reputation management; discovering and predicting consumer and voting trends; analyzing client discourse in therapy and counseling; determining relations between scientific texts by finding reasons for citations; generating more appropriate texts and making agents more believable; and creating writers' aids. The studies reported here are carried out on different languages such as English, French, Japanese, and Portuguese. Difficult challenges remain, however. It can be argued that analyzing attitude and affect in text is an "NLP"-complete problem.

InhaltsangabePreface *.- 1. Contextual Valence Shifters, Livia Polanyi, Annie Zaenen *.- 1. Introduction *.- 2. From Simple Valence to Contextually Determined Valence *.- 3. Contextual Valence Shifters *.- 4. Conclusion *.- 2. Conveying Attitude with Reported Speech, Sabine Bergler *.- 1. Introduction *.- 2. Evidential Analysis of Reported Speech *.- 3. Profile Structure *.- 4. Extended Example *.- 5. Source List Annotation *.- 6. Extension to Other Attribution *.- 7. Conclusion *.- 3. Where Attitudinal Expressions Get their Attitude, Jussi Karlgren, Gunnar Eriksson, Kristofer Franzén *.- 1. Research Questions to Motivate the Study of Attitudinal Expressions *.- 2. Starting Points - Prototypical Attitudinal Expressions *.- 3. Text Topicality: Players *.- 4. Text Topicality: Moves *.- 5. Identifying Players *.- 6. The Case for Animacy: Adjectival Attributes and Genitive Attributes *.- 7. The Case for Syntactic Structure: Situational Reference *.- 8. Using Syntactic Patterns more Systematically *.- 9. Generalizing from Syntactic Patterns to the Lexicon *.- 10. Conclusions *.- 4. Analysis of Linguistic Features Associated with Point of View for Generating Stylistically Appropriate Text, Nancy L. Green *.- 1. Introduction *.- 2. Perspectives in Corpus *.- 3. Associated Features *.- 4. Implications for Natural Language Generation and Automatic Recognition of Point of View *.- 5. The Subjectivity of Lexical Cohesion in Text, Jane Morris, Graeme Hirst *.- 1. Introduction *.- 2. Theoretical Background *.- 3. Experimental Study *.- 4. Discussion *.- 6. A Weighted Referential Activity Dictionary, Wilma Bucci, Bernard Maskit *.- 1. Introduction *.- 2. Methods *.- 3. Results *.- 7. Certainty Identification in Texts: Categorization Model and Manual Tagging Results, Victoria L. Rubin, Elizabeth D. Liddy, Noriko Kando *.- 1. Analytical Framework *.- 2. Proposed Certainty Categorization Model *.- 3. Empirical Study *.- 4. Applications *.- 5. Conclusions and Future Work *.- 8. Evaluatingan Opinion Annotation Scheme Using a New Multi-Perspective Question and Answer Corpus, Veselin Stoyanov, Claire Cardie, Diane Litman, Janyce Wiebe *.- 1. Introduction *.- 2. Low-Level Perspective Information *.- 3. The MPQA NRRC Corpus *.- 4. Multi-Perspective Question and Answer Corpus Creation *.- 5. Evaluation of Perspective Annotations for MPQA *.- 6. Conclusions and Future Work *.- 9. Validating the Coverage of Lexical Resources for Affect Analysis and Automatically Classifying New Words along Semantic Axes, Gregory Grefenstette, Yan Qu, David A. Evans, James G. Shanahan *.- 1. Introduction *.- 2. The Current Clairvoyance Affect Lexicon *.- 3. Emotive Patterns *.- 4. Scoring the Intensity of Candidate Affect Words *.- 5. Future Work *.- 6. Conclusions *.- 10. A Computational Semantic Lexicon of French Verbs of Emotion, Yvette Yannick Mathieu *.- 1. Introduction *.- 2. Semantic Lexicon Description *.- 3. FEELING System *.- 4. Evaluation *.- 5. Related Work *.- 6. Conclusion *.- 11. Extracting Opinion Propositions and Opinion Holders using Syntactic and Lexical Cues, Steven Bethard, Hong Yu, Ashley Thornton, Vasileios Hatzivassiloglou, Dan Jurafsky *.- 1. Introduction *.- 2. Data *.- 3. Opinion-Oriented Words *.- 4. Identifying Opinion Propositions *.- 5. Results *.- 6. Error Analysis *.- 7. Discussion *.- 12. Approaches for Automatically Tagging Affect, Nathanael Chambers, Joel Tetreault, James Allen *.- 1. Introduction *.- 2. Background *.- 3. Rochester Marriage-Counseling Corpus *.- 4. Approaches to Tagging *.- 5. Evaluations *.- 6. Discussion *.- 7. CATS Tool *.- 8. Related Work *.- 9. Conclusion *.- 13. Argumentative Zoning for Improved Citation Indexing, Simone Teufel *.- 1. Citation Indexing and Citation Maps *.- 2. Argumentative Zoning and Author Affect *.- 3. Meta-discourse *.- 4. Human Annotation of Author Affect *.- 5. Features for Author Affect *.- 6. Evaluation *.- 7. Conclusion *.- 14. Politeness and bias in dialogue summarization: two e