A Unified Model for Topics, Events and Users on Twitter

Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1869–1879, Seattle, Washington, USA, 18-21 October 2013. c⃝2013 Association for Computational Linguistics A Unified Model for Topics, Events and Users on Twitter Qiming Diao Living Analytics Research Centre School of Information System Singapore Management University qiming.diao.2010@smu.edu.sg Jing Jiang Living Analytics Research Centre School of Information System Singapore Management University jingjiang@smu.edu.sg Abstract With the rapid growth of social media, Twitter has become one of the most widely adopted platforms for people to post short and instant message. On the one hand, people tweets about their daily lives, and on the other hand, when major events happen, people also fol- low and tweet about them. Moreover, people’s posting behaviors on events are often closely tied to their personal interests. In this paper, we try to model topics, events and users on Twitter in a unified way. We propose a model which combines an LDA-like topic model and the Recurrent Chinese Restaurant Process to capture topics and events. We further propose a duration-based regularization component to find bursty events. We also propose to use event-topic affinity vectors to model the asso- ciation between events and topics. Our exper- iments shows that our model can accurately identify meaningful events and the event-topic affinity vectors are effective for event recom- mendation and grouping events by topics. 1 Introduction Twitter is arguably the most popular microblog site where people can post short, instant messages to share with families, friends and the rest of the world. For content analysis on Twitter, two impor- tant concepts have been repeatedly visited: (1) Top- ics. These are longstanding themes that many per- sonal tweets revolve around. Example topics range from music and sports to more serious ones like pol- itics and religion. Much work has been done to an- alyze topics on Twitter (Ramage et al., 2010; Hong and Davison, 2010; Zhao et al., 2011; Lau et al., 2012). (2) Events. These are things that take place at a certain time and attract many people’s short- term attention in social media. Example events in- clude concerts, sports games, scandals and elections. Event detection on Twitter has been a hot research topic in recent years (Petrovi´c et al., 2010; Weng and Lee, 2011; Becker et al., 2011; Diao et al., 2012; Li et al., 2012). The concepts of topics and events are orthogonal in that many events fall under certain topics. For example, concerts fall under the topic about mu- sic. Furthermore, being social media, Twitter users play important roles in forming topics and events on Twitter. Each user has her own topic interests, which influence the content of her tweets. Whether a user publishes a tweet related to an event also largely de- pends on whether her topic interests match the na- ture of the event. Modeling the interplay between topics, events and users can deepen our understand- ing of Twitter content and potentially aid many pred- ication and recommendation tasks. In this paper, we aim to …

Content truncated to 500 words