Recognizing Stances in Online Debates

Proceedings of the 47th Annual Meeting of the ACL and the 4th IJCNLP of the AFNLP, pages 226–234, Suntec, Singapore, 2-7 August 2009. c⃝2009 ACL and AFNLP Recognizing Stances in Online Debates Swapna Somasundaran Dept. of Computer Science University of Pittsburgh Pittsburgh, PA 15260 swapna@cs.pitt.edu Janyce Wiebe Dept. of Computer Science University of Pittsburgh Pittsburgh, PA 15260 wiebe@cs.pitt.edu Abstract This paper presents an unsupervised opin- ion analysis method for debate-side clas- sification, i.e., recognizing which stance a person is taking in an online debate. In order to handle the complexities of this genre, we mine the web to learn associa- tions that are indicative of opinion stances in debates. We combine this knowledge with discourse information, and formu- late the debate side classification task as an Integer Linear Programming problem. Our results show that our method is sub- stantially better than challenging baseline methods. 1 Introduction This paper presents a method for debate-side clas- sification, i.e., recognizing which stance a per- son is taking in an online debate posting. In on- line debate forums, people debate issues, express their preferences, and argue why their viewpoint is right. In addition to expressing positive sentiments about one’s preference, a key strategy is also to express negative sentiments about the other side. For example, in the debate “which mobile phone is better: iPhone or Blackberry,” a participant on the iPhone side may explicitly assert and rationalize why the iPhone is better, and, alternatively, also ar- gue why the Blackberry is worse. Thus, to recog- nize stances, we need to consider not only which opinions are positive and negative, but also what the opinions are about (their targets). Participants directly express their opinions, such as “The iPhone is cool,” but, more often, they mention associated aspects. Some aspects are par- ticular to one topic (e.g., Active-X is part of IE but not Firefox), and so distinguish between them. But even an aspect the topics share may distin- guish between them, because people who are pos- itive toward one topic may value that aspect more. For example, both the iPhone and Blackberry have keyboards, but we observed in our corpus that pos- itive opinions about the keyboard are associated with the pro Blackberry stance. Thus, we need to find distinguishing aspects, which the topics may or may not share. Complicating the picture further, participants may concede positive aspects of the opposing is- sue or topic, without coming out in favor of it, and they may concede negative aspects of the is- sue or topic they support. For example, in the fol- lowing sentence, the speaker says positive things about the iPhone, even though he does not pre- fer it: “Yes, the iPhone may be cool to take it out and play with and show off, but past that, it offers nothing.” Thus, we need to consider discourse re- lations to sort out which sentiments in fact reveal the writer’s stance, and which are merely conces- sions. Many opinion mining approaches find negative and positive words …

Content truncated to 500 words