Identifying and classifying subjective claims

ABSTRACT

To understand the subjective documents, for example, public comments on the government's proposed regulation, opinion identification and classification is required. Rather than classifying documents or sentences into binary polarities as in much previous work, we identify the main claim or assertion of the writer and classify it into the predefined classes of opinion (attitude) over the topic. For the classification of the claims, we automatically build a list of multi-word subjective expressions by extending a small set of seed words, using automatically generated paraphrases from machine translation corpus. Our supervised machine learning method shows significant improvement over the baseline both in identification and classification of claims.

REFERENCES

• 1: Collin F. Baker , Charles J. Fillmore , John B. Lowe, The Berkeley FrameNet Project, Proceedings of the 17th international conference on Computational linguistics, August 10-14, 1998, Montreal, Quebec, Canada
• 2: Jill Burstein , Daniel Marcu , Slava Andreyev , Martin Chodorow, Towards automatic classification of discourse elements in essays, Proceedings of the 39th Annual Meeting on Association for Computational Linguistics, p.98-105, July 06-11, 2001, Toulouse, France [doi>10.3115/1073012.1073026]
• 3: Eugene Charniak, A maximum-entropy-inspired parser, Proceedings of the first conference on North American chapter of the Association for Computational Linguistics, p.132-139, April 29-May 04, 2000, Seattle, Washington
• 4: Cohen, J. A Coefficient of Agreement for Nominal Scales. Education and Psychological Measurement. 43(6):37--46. 1960.
• 5: General Inquirer. http://www.wjh.harvard.edu/inquirer/.
• 6: Soo-Min Kim , Eduard Hovy, Determining the sentiment of opinions, Proceedings of the 20th international conference on Computational Linguistics, p.1367-es, August 23-27, 2004, Geneva, Switzerland [doi>10.3115/1220355.1220555]
• 7: Namhee Kwon , Stuart W. Shulman , Eduard Hovy, Multidimensional text analysis for eRulemaking, Proceedings of the 2006 international conference on Digital government research, May 21-24, 2006, San Diego, California [doi>10.1145/1146598.1146649]
• 8: Ron Meir , Gunnar Rätsch, An introduction to boosting and leveraging, Advanced lectures on machine learning, Springer-Verlag New York, Inc., New York, NY, 2003
• 9: Mishne, G. Experiments with Mood Classification in Blog Posts. In Proceedings of the 1^st Workshop on Stylistic Analysis of Text for Information Access at SIGIR. Salvador, Brazil, 2005.
• 10: Franz Josef Och , Hermann Ney, A systematic comparison of various statistical alignment models, Computational Linguistics, v.29 n.1, p.19-51, March 2003 [doi>10.1162/089120103321337421]
• 11: Franz Josef Och , Hermann Ney, The Alignment Template Approach to Statistical Machine Translation, Computational Linguistics, v.30 n.4, p.417-449, December 2004 [doi>10.1162/0891201042544884]
• 12: Bo Pang , Lillian Lee , Shivakumar Vaithyanathan, Thumbs up?: sentiment classification using machine learning techniques, Proceedings of the ACL-02 conference on Empirical methods in natural language processing, p.79-86, July 06, 2002 [doi>10.3115/1118693.1118704]
• 13: Bo Pang , Lillian Lee, Seeing stars: exploiting class relationships for sentiment categorization with respect to rating scales, Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, p.115-124, June 25-30, 2005, Ann Arbor, Michigan [doi>10.3115/1219840.1219855]
• 14: Robert E. Schapire , Yoram Singer, BoosTexter: A Boosting-based Systemfor Text Categorization, Machine Learning, v.39 n.2-3, p.135-168, May-June 2000 [doi>10.1023/A:1007649029923]
• 15: Shulman, S. W. e-Rulemaking: Issues in Current Research and Practice. International Journal of Public Administration 28:621--641. 2005.
• 16: Peter D. Turney , Michael L. Littman, Measuring praise and criticism: Inference of semantic orientation from association, ACM Transactions on Information Systems (TOIS), v.21 n.4, p.315-346, October 2003 [doi>10.1145/944012.944013]
• 17: Vladimir N. Vapnik, The nature of statistical learning theory, Springer-Verlag New York, Inc., New York, NY, 1995
• 18: Janyce Wiebe , Theresa Wilson , Rebecca Bruce , Matthew Bell , Melanie Martin, Learning Subjective Language, Computational Linguistics, v.30 n.3, p.277-308, September 2004 [doi>10.1162/0891201041850885]
• 19: Wilson, T., Wiebe, J., and Hwa, R. Just How Mad are You? Finding Strong and Weak Opinion Clauses. In Proceedings of AAAI-04. San Jose, CA, 2004.
• 20: Theresa Wilson , Janyce Wiebe , Paul Hoffmann, Recognizing contextual polarity in phrase-level sentiment analysis, Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing, p.347-354, October 06-08, 2005, Vancouver, British Columbia, Canada [doi>10.3115/1220575.1220619]
• 21: Hui Yang , Jamie Callan, Near-duplicate detection for eRulemaking, Proceedings of the 2005 national conference on Digital government research, May 15-18, 2005, Atlanta, Georgia
• 22: Hui Yang , Jamie Callan , Stuart Shulman, Next steps in near-duplicate detection for eRulemaking, Proceedings of the 2006 international conference on Digital government research, May 21-24, 2006, San Diego, California [doi>10.1145/1146598.1146663]
• 23: Hong Yu , Vasileios Hatzivassiloglou, Towards answering opinion questions: separating facts from opinions and identifying the polarity of opinion sentences, Proceedings of the 2003 conference on Empirical methods in natural language processing, p.129-136, July 11, 2003 [doi>10.3115/1119355.1119372]
• 24: Zhou, L., Lin, C., Munteanu, D. S., and Hovy, E. http://www.isi.edu/~liangz/DEMO/PARA/, 2006.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.7 Natural Language Processing

General Terms:
Algorithms, Experimentation, Languages

Keywords:
electronic rulemaking, opinion, public comments, text annotation