Topic transition detection about the East Japan great earthquake based on emerging modularity over time

Social media, in which individual users post their opinions and gradually build their consensus, is recognised as one of pervasive collaboration. Tracking topic transitions over time on a social media provides a rich insight into exploring its social context. This paper proposes a novel approach using a modularity measure which shows the quality of a division of a network into modules, for topic transition detection. In this method, first, significant topical terms are extracted from messages in social media. Next, a snapshot cooccurrence network is constructed at each time stamp. Then, hierarchical topic structures for each snapshot network are organised by a modularity measure. Words' similarities are considered by cosine similarity, and topic similarities are calculated using Jaccard coefficient. An experiment was conducted for messages related to the East Japan great earthquake in a buzz marketing site, and the effectiveness of our proposed method was shown.