Online Bursty Event Detection from Microblog

Microblogs (e.g., Twitter and Weibo) have become a large social media platform for users to share contents, their interests and events with friends. A surge of the number of event related posts always reflects that some people's concern real-life events happened. In this paper, we propose an incremental temporal topic model for microblogs namely BEE (Bursty Event dEtection) to detect these bursty events. BEE supports to detect these bursty events from short text datasets through modeling the temporal information of events. And BEE employs processing the post streaming incrementally to track the topic of events drifting over time. Therefore, the latent semantic indices are preserved from one time period to the next. After BEE detects the event-driven posts and related events, the bursty detection module can identify the bursty patterns for each event and rank the events using the bursty patterns. Our experiments on a large Weibo dataset show that our algorithm can outperform the baselines for detecting the meaningful bursty events. Subsequently, we also show some case studies that indicate the effectiveness of the temporal factor for bursty event detection and how well BEE can track the topic drifting of events.