Belief surveillance with Twitter

• Authors: Sanmitra Bhattacharya;Hung Tran;Padmini Srinivasan;Jerry Suls
• Venue: Proceedings of the 3rd Annual ACM Web Science Conference
• Year: 2012

Data from social media systems are being actively mined for trends and patterns of interests. Problems such as sentiment and opinion mining, and prediction of election outcomes have become tremendously popular due to the unprecedented availability of social interactivity data of different types. An important angle that has not yet been explored is to estimate beliefs from posts made on social media. We propose that social media can be used to monitor the level of belief, disbelief and doubt related to specific propositions. Inspired by efforts in disease surveillance using social media we coin the term belief surveillance for this function. We propose a novel methodological framework for belief surveillance using Twitter. Our method may be used to gauge belief on any proposition as long as it is specifiable in a form that we call probes. We present our belief estimates for 32 probes some of which represent factual information, others represent false information and the remaining represent debatable propositions. Finally, we provide preliminary evidence suggesting that off-the-shelf classifiers may be used to automatically estimate belief.