Self-disclosure topic model for classifying and analyzing Twitter conversations

Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1986–1996, October 25-29, 2014, Doha, Qatar. c⃝2014 Association for Computational Linguistics Self-disclosure topic model for classifying and analyzing Twitter conversations JinYeong Bak∗ Department of Computer Science KAIST Daejeon, South Korea jy.bak@kaist.ac.kr Chin-Yew Lin Microsoft Research Beijing 100080, P.R. China cyl@microsoft.com Alice Oh Department of Computer Science KAIST Daejeon, South Korea alice.oh@kaist.edu Abstract Self-disclosure, the act of revealing one- self to others, is an important social be- havior that strengthens interpersonal rela- tionships and increases social support. Al- though there are many social science stud- ies of self-disclosure, they are based on manual coding of small datasets and ques- tionnaires. We conduct a computational analysis of self-disclosure with a large dataset of naturally-occurring conversa- tions, a semi-supervised machine learning algorithm, and a computational analysis of the effects of self-disclosure on subse- quent conversations. We use a longitu- dinal dataset of 17 million tweets, all of which occurred in conversations that con- sist of five or more tweets directly reply- ing to the previous tweet, and from dyads with twenty of more conversations each. We develop self-disclosure topic model (SDTM), a variant of latent Dirichlet al- location (LDA) for automatically classi- fying the level of self-disclosure for each tweet. We take the results of SDTM and analyze the effects of self-disclosure on subsequent conversations. Our model sig- nificantly outperforms several comparable methods on classifying the level of self- disclosure, and the analysis of the longitu- dinal data using SDTM uncovers signifi- cant and positive correlation between self- disclosure and conversation frequency and length. 1 Introduction Self-disclosure is an important and pervasive so- cial behavior. People disclose personal informa- tion about themselves to improve and maintain ∗This work was done when JinYeong Bak was a visiting student at Microsoft Research, Beijing, China. relationships (Jourard, 1971; Joinson and Paine, 2007). A common instance of self-disclosure is the start of a conversation with an exchange of names and additional self-introductions. Another example of self-disclosure, shown in Figure 1c, where the information disclosed about a family member’s serious illness, is much more personal than the exchange of names. In this paper, we seek to understand this important social behavior using a large-scale Twitter conversation data, automati- cally classifying the level of self-disclosure using machine learning and correlating the patterns with conversational behaviors which can serve as prox- ies for measuring intimacy between two conversa- tional partners. Twitter conversation data, explained in more detail in section 4.1, enable an extremely large scale study of naturally-occurring self-disclosure behavior, compared to traditional social science studies. One challenge of such large scale study, though, remains in the lack of labeled ground- truth data of self-disclosure level. That is, naturally-occurring Twitter conversations do not come tagged with the level of self-disclosure in each conversation. To overcome that challenge, we propose a semi-supervised machine learning approach using probabilistic topic modeling. Our self-disclosure topic model (SDTM) assumes that self-disclosure behavior can be modeled using a combination of simple linguistic …

Content truncated to 500 words