Computing Attitude and Affect in Text: Theory and Applications

• Συγγραφή απο Οργανισμό/Αρχή: SpringerLink (Online service)
• Άλλοι συγγραφείς: Shanahan, James G. (Επιμελητής έκδοσης), Qu, Yan (Επιμελητής έκδοσης), Wiebe, Janyce (Επιμελητής έκδοσης)
• Μορφή: Ηλεκτρονική πηγή Ηλ. βιβλίο
• Γλώσσα: English
• Έκδοση: Dordrecht : Springer Netherlands, 2006.
• Σειρά: The Information Retrieval Series, 20
• Θέματα: Computer science.; Library science.; Information storage and retrieval.; Artificial intelligence.; Computational linguistics.; Computer Science.; Information Storage and Retrieval.; Library Science.; Computer Science, general.; Information Systems Applications (incl. Internet).; Artificial Intelligence (incl. Robotics).; Language Translation and Linguistics.

 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. 

 Contextual Valence Shifters -- Conveying Attitude with Reported Speech -- Where Attitudinal Expressions Get their Attitude -- Analysis of Linguistic Features Associated with Point of View for Generating Stylistically Appropriate Text -- The Subjectivity of Lexical Cohesion in Text -- A Weighted Referential Activity Dictionary -- Certainty Identification in Texts: Categorization Model and Manual Tagging Results -- Evaluating an Opinion Annotation Scheme Using a New Multi-Perspective Question and Answer Corpus -- Validating the Coverage of Lexical Resources for Affect Analysis and Automatically Classifying New Words along Semantic Axes -- A Computational Semantic Lexicon of French Verbs of Emotion -- Extracting Opinion Propositions and Opinion Holders using Syntactic and Lexical Cues -- Approaches for Automatically Tagging Affect: Steps Toward an Effective and Efficient Tool -- Argumentative Zoning for Improved Citation Indexing -- Politeness and Bias in Dialogue Summarization: Two Exploratory Studies -- Generating More-Positive and More-Negative Text -- Identifying Interpersonal Distance using Systemic Features -- Corpus-Based Study of Scientific Methodology: Comparing the Historical and Experimental Sciences -- Argumentative Zoning Applied to Critiquing Novices’ Scientific Abstracts -- Using Hedges to Classify Citations in Scientific Articles -- Towards a Robust Metric of Polarity -- Characterizing Buzz and Sentiment in Internet Sources: Linguistic Summaries and Predictive Behaviors -- Good News or Bad News? Let the Market Decide -- Opinion Polarity Identification of Movie Reviews -- Multi-Document Viewpoint Summarization Focused on Facts, Opinion and Knowledge.