Identifying sources of opinions with conditional random fields and extraction patterns
Open Access
- 1 January 2005
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 355-362
Abstract
Recent systems have been developed for sentiment classification, opinion recognition, and opinion analysis (e.g., detecting polarity and strength). We pursue another aspect of opinion analysis: identifying the sources of opinions, emotions, and sentiments. We view this problem as an information extraction task and adopt a hybrid approach that combines Conditional Random Fields (Lafferty et al., 2001) and a variation of AutoSlog (Riloff, 1996a). While CRFs model source identification as a sequence tagging task, Au-toSlog learns extraction patterns. Our results show that the combination of these two methods performs better than either one alone. The resulting system identifies opinion sources with 79.3% precision and 59.5% recall using a head noun matching measure, and 81.2% precision and 60.6% recall using an overlap measure.Keywords
This publication has 6 references indexed in Scilit:
- Annotating Expressions of Opinions and Emotions in LanguageLanguage Resources and Evaluation, 2005
- Creating Subjective and Objective Sentence Classifiers from Unannotated Texts2005
- Playing the telephone game2004
- Head-Driven Statistical Models for Natural Language ParsingComputational Linguistics, 2003
- Learning extraction patterns for subjective expressions2003
- English verb classes and alternations: A preliminary investigation. By Beth Levin. Chicago: University of Chicago Press, 1993. Pp. xviii, 345. Cloth $45.00, paper $18.95.Language, 1995