Complex Adaptive Systems, Publication 4 Cihan H. Dagli, Editor in Chief Conference Organized by Missouri Univ ersity of Science and Technology 2014- Philadelphia, PA Controversial Topic Discovery on Members of Congress with Twitter

Abstract This paper addresses how Twitter can be used for identifying conflict between communities of users. We aggregate documents by topic and by community and perform sentiment analysis, which allows us to analyze the overall opinion of each community about each topic. We rank the topics with opposing views (negative for one community and positive for the other). For illustration of the proposed methodology we chose a problem whose results can be evaluated using news articles. We look at tweets for republican and democrat congress members for the 112 th House of Representatives from September to December 2013 and demonstrate that our approach is successful by comparing against articlesin the news media. Keywords Twitter; Latent Dirichlet Allocation; Topic Modeling; Polarizing Topics; Semantic Extraction; Social Media Mining : 1. Introduction witter has become an important social media site since it T s inception in 2006. It is a micro blogging service, which allows users to post messages up to 140 characters known as tweets. Twitter users are followed and are themselves following others, thus creating a social network. This social network can be used to identify communities. Are there communities in this network with opposing views? How do we identify such communities? How do we aggregate sufficient information from micro blogs to assess if the communities have opposite views? Twisers typically tune in to listen to popular, smart, tter u informative members of society. In this paper we don’t analyze the Big Data problem that is associated with listening to all of Twitter; we simply focus on a small set of informative Twitter accounts that belong to members of 112