Modeling and Predicting the Re-post Behavior in Sina Weibo

Study of human behavior patterns is of utmost importance to many areas, such as disease spread, resource allocation, and emergency response. Because of its widespread availability and use, online social networks (OSNs) have become an attractive proxy for studying human behaviors. One of the interesting and challenging problems about OSNs is that how much attention of a post from a user can gain? In this paper, we try to tackle this issue by exploring approaches to predict the amount of reposts any given post will obtain in Sina Weibo, a famous microblogging service in China. Specifically, we propose a Reposts Tree based method to model the reposting process in a temporal dynamic manner. Experiments over the real world collected data indicate that our method is effective on repost predicting.