Computing Attitude and Affect in Text: Theory and Applications

1. Front Matter

   Pages i-xvi

   PDF

2. Contextual Valence Shifters

   • Livia Polanyi, Annie Zaenen

   Pages 1-10

3. Conveying Attitude with Reported Speech

   • Sabine Bergler

   Pages 11-22

4. Where Attitudinal Expressions Get their Attitude

   • Jussi Karlgren, Gunnar Eriksson, Kristofer Franzén

   Pages 23-31

5. Analysis of Linguistic Features Associated with Point of View for Generating Stylistically Appropriate Text

   • Nancy L. Green

   Pages 33-39

6. The Subjectivity of Lexical Cohesion in Text

   • Jane Morris, Graeme Hirst

   Pages 41-47

7. A Weighted Referential Activity Dictionary

   • Wilma Bucci, Bernard Maskit

   Pages 49-60

8. Certainty Identification in Texts: Categorization Model and Manual Tagging Results

   • Victoria L. Rubin, Elizabeth D. Liddy, Noriko Kando

   Pages 61-76

9. Evaluating an Opinion Annotation Scheme Using a New Multi-Perspective Question and Answer Corpus

   • Veselin Stoyanov, Claire Cardie, Diane Litman, Janyce Wiebe

   Pages 77-91

10. 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

    Pages 93-107

11. A Computational Semantic Lexicon of French Verbs of Emotion

    • Yvette Yannick Mathieu

    Pages 109-124

12. Extracting Opinion Propositions and Opinion Holders using Syntactic and Lexical Cues

    • Steven Bethard, Hong Yu, Ashley Thornton, Vasileios Hatzivassiloglou, Dan Jurafsky

    Pages 125-141

13. Approaches for Automatically Tagging Affect: Steps Toward an Effective and Efficient Tool

    • Nathanael Chambers, Joel Tetreault, James Allen

    Pages 143-158

14. Argumentative Zoning for Improved Citation Indexing

    • Simone Teufel

    Pages 159-169

15. Politeness and Bias in Dialogue Summarization: Two Exploratory Studies

    • Norton Trevisan Roman, Paul Piwek, Ariadne Maria Brito Rizzoni Carvalho

    Pages 171-185

16. Generating More-Positive and More-Negative Text

    • Diana Zaiu Inkpen, Ol’ga Feiguina, Graeme Hirst

    Pages 187-198

17. Identifying Interpersonal Distance using Systemic Features

    • Casey Whitelaw, Jon Patrick, Maria Herke-Couchman

    Pages 199-214

18. Corpus-Based Study of Scientific Methodology: Comparing the Historical and Experimental Sciences

    • Shlomo Argamon, Jeff Dodick

    Pages 215-231

19. Argumentative Zoning Applied to Critiquing Novices’ Scientific Abstracts

    • Valéria D. Feltrim, Simone Teufel, Maria Graças V. das Nunes, Sandra M. Aluísio

    Pages 233-246

20. Using Hedges to Classify Citations in Scientific Articles

    • Chrysanne Di Marco, Frederick W. Kroon, Robert E. Mercer

    Pages 247-263

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.

• Text
• artificial intelligence
• berck
• corpus
• intelligence
• natural language processing
• therapy

From the reviews:

"The volume contains 24 extended versions of papers that were originally presented at the American Association for Artificial Intelligence (AAAI) … . should become an indispensable resource for anyone interested in this area. Whether the reader is more interested in the computational or the linguistic aspects of the problem-or even just the range of possible applications-this collection will broaden the perspective on the issue. For readers with no background in sentiment detection the volume can serve as an initial overview of the field … ." (Michael Gamon, Computational Linguistics, Vol. 33 (2), 2007)

 

"...this volume shines as truly presenting cutting-edge research in a specific subfield within NLP. The editors have done a fine job in aggregating full-length papers that are both interesting and informative from established researchers in the field." (from the ACM Reviews by Robert Goldberg, Queens College, NY, USA)

• Clairvoyance Cooperation, Pittsburgh, USA

  James G. Shanahan, Yan Qu

• University of Pittsburgh, USA

  Janyce Wiebe

Policies and ethics