tailieunhanh - Báo cáo khoa học: "Recognizing Stances in Online Debates"

This paper presents an unsupervised opinion analysis method for debate-side classification, ., 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 associations that are indicative of opinion stances in debates. We combine this knowledge with discourse information, and formulate the debate side classification task as an Integer Linear Programming problem. Our results show that our method is substantially better than challenging baseline methods. . | Recognizing Stances in Online Debates Swapna Somasundaran Dept. of Computer Science University of Pittsburgh Pittsburgh PA 15260 swapna@ Janyce Wiebe Dept. of Computer Science University of Pittsburgh Pittsburgh PA 15260 wiebe@ Abstract This paper presents an unsupervised opinion analysis method for debate-side classification . 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 associations that are indicative of opinion stances in debates. We combine this knowledge with discourse information and formulate the debate side classification task as an Integer Linear Programming problem. Our results show that our method is substantially better than challenging baseline methods. 1 Introduction This paper presents a method for debate-side classification . recognizing which stance a person is taking in an online debate posting. In online 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 argue why the Blackberry is worse. Thus to recognize 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 particular to one topic . Active-X is part of IE but not Firefox and so distinguish between them. But even an aspect the topics share may distinguish between them because people who are positive toward one topic may value that aspect more. For example both the iPhone and .