Using explicit linguistic expressions of preference in social media to predict voting behavior

Probably the major approach to making predictions or recommendations about user behavior is by pairing unambiguous indicators of preference with attributes of the users who have given those indications. However, since the necessary preference data is often difficult to obtain, it is considered very valuable and often held closely by vendors and advertisers. On the other hand, while Twitter and other social media platforms provide a wealth of data about users by way of what they say or tweet, who or what they like or follow, etc., little work has been done to combine these data with indicators of preference for purposes of prediction or recommendation. In this paper we present a novel approach to mining preference data from natural language expressions in social media, which are then extrapolated to other individuals whose preferences are not known through predictive modeling. As an application for this approach, we describe the implementation of Tweetcast Your Vote, a publicly accessible system that predicted the voting decisions of Twitter users in the 2012 U.S. presidential election.