Unifying Local and Global Agreement and Disagreement Classification in Online Debates
作者： Cecile Paris , Paul Thomas , Nalin Narang , Jie Yin
DOI:
关键词:
摘要: Online debate forums provide a powerful communication platform for individual users to share information, exchange ideas and express opinions on variety of topics. Understanding people's in such is an important task as its results can be used many ways. It is, however, challenging because the informal language use dynamic nature online conversations. In this paper, we propose new method identifying participants' agreement or disagreement issue by exploiting information contained each posts. Our proposed first regards post local context, then aggregates posts estimate participant's overall position. We have explored sentiment, emotional durational features improve accuracy automatic classification. experimental shown that aggregating positions over yields better performance than non-aggregation baselines when users' global issue.
aclweb.org参考文章(16)
David P. Redlawsk, Ramnath Balasubramanyan, William W. Cohen, Doug Pierce, What pushes their buttons? Predicting comment polarity from the content of political blog posts Proceedings of the Workshop on Language in Social Media (LSM 2011). pp. 12- 19 ,(2011)
Andrea Esuli, Stefano Baccianella, Fabrizio Sebastiani, SentiWordNet 3.0: An Enhanced Lexical Resource for Sentiment Analysis and Opinion Mining. language resources and evaluation. ,(2010)
Tong Zhang, Frank J. Oles, Text Categorization Based on Regularized Linear Classification Methods Information Retrieval. ,vol. 4, pp. 5- 31 ,(2001) , 10.1023/A:1011441423217
S. Sathiya Keerthi, Chih-Jen Lin, Ruby C. Weng, Trust Region Newton Method for Logistic Regression Journal of Machine Learning Research. ,vol. 9, pp. 627- 650 ,(2008) , 10.1145/1390681.1390703
Akiko Murakami, Rudy Raymond, Support or Oppose? Classifying Positions in Online Debates from Reply Activities and Opinion Expressions international conference on computational linguistics. pp. 869- 875 ,(2010)
Matt Thomas, Bo Pang, Lillian Lee, Get out the vote: Determining support or opposition from Congressional floor-debate transcripts empirical methods in natural language processing. pp. 327- 335 ,(2006) , 10.3115/1610075.1610122
Rakesh Agrawal, Sridhar Rajagopalan, Ramakrishnan Srikant, Yirong Xu, Mining newsgroups using networks arising from social behavior Proceedings of the twelfth international conference on World Wide Web - WWW '03. pp. 529- 535 ,(2003) , 10.1145/775152.775227
Swapna Somasundaran, Janyce Wiebe, Recognizing Stances in Ideological On-Line Debates north american chapter of the association for computational linguistics. pp. 116- 124 ,(2010)
Michel Galley, Kathleen McKeown, Julia Hirschberg, Elizabeth Shriberg, Identifying Agreement and Disagreement in Conversational Speech: Use of Bayesian Networks to Model Pragmatic Dependencies meeting of the association for computational linguistics. pp. 669- 676 ,(2004) , 10.3115/1218955.1219040
Rong-En Fan, Kai-Wei Chang, Cho-Jui Hsieh, Chih-Jen Lin, Xiang-Rui Wang, LIBLINEAR: A Library for Large Linear Classification Journal of Machine Learning Research. ,vol. 9, pp. 1871- 1874 ,(2008)