Inferring user interests from tweet times

We propose and demonstrate the feasibility of a probabilistic framework for mining user interests from their tweet times alone, by exploiting the known timing of external events associated with these interests. This approach allows for making inferences on the interests of a large number of users for which text-based mining may become cumbersome, and also sidesteps the difficult problem of semantic/contextual analysis required for such text-based inferences. The statistic that we propose for gauging the user's interest level is the probability that he/she tweets more frequently at certain times when this topic is in the ``public eye'' than at other times. We report on promising experimental results using Twitter data on detecting whether or not a user is a fan of a given baseball team, leveraging the known timing of games played by the team. Since people often interact with others who share similar interests, we extend our probabilistic framework to use the interest level estimates for other users with whom a person interacts (by referring to them in his/her tweets). We demonstrate that it is possible to significantly improve the detection probability (for a given false alarm rate) by such information pooling on the social graph.