Public Dialogue: Analysis of Tolerance in Online Discussions

Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, pages 1680–1690, Sofia, Bulgaria, August 4-9 2013. c⃝2013 Association for Computational Linguistics Public Dialogue: Analysis of Tolerance in Online Discussions Arjun Mukherjee† Vivek Venkataraman† Bing Liu† Sharon Meraz‡ †Department of Computer Science ‡Department of Communication University of Illinois at Chicago arjun4787@gmail.com {vvenka6, liub, smeraz}@uic.edu Abstract Social media platforms have enabled people to freely express their views and discuss issues of interest with others. While it is important to dis- cover the topics in discussions, it is equally use- ful to mine the nature of such discussions or de- bates and the behavior of the participants. There are many questions that can be asked. One key question is whether the participants give rea- soned arguments with justifiable claims via constructive debates or exhibit dogmatism and egotistic clashes of ideologies. The central idea of this question is tolerance, which is a key concept in the field of communications. In this work, we perform a computational study of tol- erance in the context of online discussions. We aim to identify tolerant vs. intolerant partici- pants and investigate how disagreement affects tolerance in discussions in a quantitative framework. To the best of our knowledge, this is the first such study. Our experiments using real-life discussions demonstrate the effective- ness of the proposed technique and also provide some key insights into the psycholinguistic phenomenon of tolerance in online discussions. 1 Introduction Social media platforms have enabled people from anywhere in the world to express their views and discuss any issue of interest in online discussions/debates. Existing works in this con- text include recognition of support and oppose camps (Agrawal et al., 2003), mining of authori- ties and subgroups (Mayfield and Rosè, 2011; Abu-Jbara et al. (2012), dialogue act segmenta- tion and classification (Morbini and Sagae, 2011; Boyer et al., 2011), etc. This paper probes further to study a different and important angle, i.e., the psycholinguistic phenomenon of tolerance in online discussions. Tolerance is an important concept in the field of communications. It is a subfacet of deliberation which refers to critical thinking and exchange of rational arguments on an issue among partici- pants that seek to achieve consensus/solution (Habermas, 1984). Perhaps the most widely accepted definition of tolerance is that of Gastil (2005; 2007), who defines tolerance as a means to engage (in writ- ten or spoken communication) in critical think- ing, judicious argument, sound reasoning, and justifiable claims through constructive discus- sion as opposed to mere coercion/egotistic clash- es of ideologies. In this work, we adopt this definition, and also employ the following characteristics of tolerance (also known as “code of conduct”) (Crocker, 2005; Gutmann and Thompson, 1996) to guide our work. Reciprocity: Each member (or participant) offers proposals and justifications in terms that others could understand and accept. Publicity: Each member engages in a process that is transparent to all and each member knows with whom he is agreeing or disagree- ing. Accountability: Each member gives acceptable and sound reasons to …

Content truncated to 500 words