Listening to the crowd: automated analysis of events via aggregated twitter sentiment

Individuals often express their opinions on social media platforms like Twitter and Facebook during public events such as the U.S. Presidential debate and the Oscar awards ceremony. Gleaning insight-s from these posts is of importance to analyzing the impact of the event. In this work, we consider the problem of identifying the segments and topic-s of an event that garnered praise or criticism, ac-cording to aggregated Twitter responses. We pro-pose a flexible factorization framework, SOCSEN-T, to learn factors about segments, topics, and sen-timents. To regulate the learning process, several constraints based on prior knowledge on sentimen-t lexicon, sentiment orientations (on a few tweets) as well as tweets alignments to the event are en-forced. We implement our approach using simple update rules to get the optimal solution. We eval-uate the proposed method both quantitatively and qualitatively on two large-scale tweet datasets as-sociated with two events from different domains to show that it improves significantly over baseline models.