Exacting Social Events for Tweets Using a Factor Graph

• DOI: 10.1609/aaai.v26i1.8350
• Publication Date: 2022-06-01T20:30:26Z
• Authors: Xiaohua Liu; Xiangyang Zhou; Zhongyang Fu; Furu Wei; Ming Zhou
• Keywords: Social network (sociolinguistics)

Social events are that occur between people where at least one person is aware of the other and event taking place. Extracting social can play an important role in a wide range applications, such as construction network. In this paper, we introduce task extraction for tweets, source fresh events. One main challenge lack information single tweet, which rooted short noise-prone nature tweets. We propose to collectively extract from multiple similar tweets using novel factor graph, harvest redundance i.e., repeated occurrences several evaluate our method on human annotated data set, show it outperforms all baselines, with absolute gain 21% F1.