Vote Prediction on Comments in Social Polls

A poll consists of a question and a set of predefined answers from which voters can select. We present the new problem of vote prediction on comments, which involves determining which of these answers a voter selected given a comment she wrote after voting. To address this task, we exploit not only the information extracted from the comments but also extra-textual information such as user demographic information and inter-comment constraints. In an evaluation involving nearly one million comments collected from the popular SodaHead social polling website, we show that a vote prediction system that exploits only textual information can be improved significantly when extended with extra-textual information.