Paper: Exploiting Community Emotion for Microblog Event Detection

ACL ID D14-1123
Title Exploiting Community Emotion for Microblog Event Detection
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2014

Microblog has become a major plat- form for information about real-world events. Automatically discovering real- world events from microblog has attracted the attention of many researchers. Howev- er, most of existing work ignore the impor- tance of emotion information for event de- tection. We argue that people?s emotion- al reactions immediately reflect the occur- ring of real-world events and should be im- portant for event detection. In this study, we focus on the problem of community- related event detection by community e- motions. To address the problem, we pro- pose a novel framework which include the following three key components: mi- croblog emotion classification, community emotion aggregation and community emo- tion burst detection. We evaluate our ap- proach on real microblog...