Online topic model for Twitter considering dynamics of user interests and topic trends

Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1977–1985, October 25-29, 2014, Doha, Qatar. c⃝2014 Association for Computational Linguistics Online Topic Model for Twitter Considering Dynamics of User Interests and Topic Trends Kentaro Sasaki, Tomohiro Yoshikawa, Takeshi Furuhashi Graduate School of Engineering Nagoya University sasaki@cmplx.cse.nagoya-u.ac.jp yoshikawa, furuhashi@cse.nagoya-u.ac.jp Abstract Latent Dirichlet allocation (LDA) is a topic model that has been applied to var- ious fields, including user profiling and event summarization on Twitter. When LDA is applied to tweet collections, it gen- erally treats all aggregated tweets of a user as a single document. Twitter-LDA, which assumes a single tweet consists of a single topic, has been proposed and has shown that it is superior in topic semantic coher- ence. However, Twitter-LDA is not capa- ble of online inference. In this study, we extend Twitter-LDA in the following two ways. First, we model the generation pro- cess of tweets more accurately by estimat- ing the ratio between topic words and gen- eral words for each user. Second, we en- able it to estimate the dynamics of user in- terests and topic trends online based on the topic tracking model (TTM), which mod- els consumer purchase behaviors. 1 Introduction Microblogs such as Twitter, have prevailed rapidly in our society recently. Twitter users post a mes- sage using 140 characters, which is called a tweet. The characters limit allows users to post tweets easily about not only personal interest or real life but also public events such as traffic accidents or earthquakes. There have been many studies on how to extract and utilize such information on tweets (Diao et al., 2012; Pennacchiotti and Popescu, 2011; Sakaki et al., 2010; Weng et al., 2010). Topic models, such as latent Dirichlet alloca- tion (LDA) (Blei et al., 2003) are widely used to identify latent topic structure in large collections of documents. Recently, some studies have ap- plied LDA to Twitter for user classification (Pen- nacchiotti and Popescu, 2011), detection of influ- ential users (Weng et al., 2010), and so on. LDA is a generative document model, which assumes that each document is represented as a probabil- ity distribution over some topics, and that each word has a latent topic. When we apply LDA to tweets, each tweet is treated as a single docu- ment. This direct application does not work well because a tweet is very short compared with tradi- tional media such as newspapers. To deal with the shortness of a tweet, some studies aggregated all the tweets of a user as a single document (Hong and Davison, 2010; Pennacchiotti and Popescu, 2011; Weng et al., 2010). On the other hand, Zhao et al. (2011) proposed “Twitter-LDA,” which is a model that considers the shortness of a tweet. Twitter-LDA assumes that a single tweet consists of a single topic, and that tweets consist of topic and background words. Zhao et al. (2011) show that it works well at the point of semantic coher- ence of topics compared with …

Content truncated to 500 words