Identifying Emotional and Informational Support in Online Health Communities

Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers, pages 827–836, Dublin, Ireland, August 23-29 2014. Identifying Emotional and Informational Support in Online Health Communities Prakhar Biyani1 Cornelia Caragea2 Prasenjit Mitra1 John Yen1 (1) College of Information Sciences and Technology, The Pennsylvania State University, USA (2) Department of Computer Science and Engineering, University of North Texas, USA pxb5080@ist.psu.edu, ccaragea@unt.edu, {pmitra,jyen}@ist.psu.edu Abstract A large number of online health communities exist today, helping millions of people with social support during difficult phases of their lives when they suffer from serious diseases. Interactions between members in these communities contain discussions on practical problems faced by peo- ple during their illness such as depression, side-effects of medications, etc and answers to those problems provided by other members. Analyzing these interactions can be helpful in getting crucial information about the community such as dominant health issues, identifying sentimental effects of interactions on individual members and identifying influential members. In this paper, we analyze user messages of an online cancer support community, Cancer Survivors Network (CSN), to identity the two types of social support present in them: emotional support and infor- mational support. We model the task as a binary classification problem. We use several generic and novel domain-specific features. Experimental results show that we achieve high classifica- tion performance. We, then, use the classifier to predict the type of support in CSN messages and analyze the posting behaviors of regular members and influential members in CSN in terms of the type of support they provide in their messages. We find that influential members generally provide more emotional support as compared to regular members in CSN. 1 Introduction Increasingly more people turn to online health communities (OHCs) to seek social support during their illnesses (LaCoursiere, 2001; Beaudoin and Tao, 2007). When people suffering from a serious disease such as cancer or AIDS interact with other people who have experienced similar medical conditions, they feel emotionally supported. In addition, through these interactions, people can obtain important information about the disease, e.g., about various medications, symptoms, and side-effects. Although authoritative health-related web sites contain the information they search for, obtaining this information directly from people in OHCs adds substantial value to it. Previous studies showed that obtaining social support in OHCs can help people feel better (Dunkel-Schetter, 1984; Maloney-Krichmar and Preece, 2005; Beaudoin and Tao, 2007; Vilhauer, 2009; Qiu et al., 2011). As a result of online interactions in OHCs, a huge volume of user-generated content exists today on various issues/problems related to specific diseases. This content comprises of important information such as people’s experiences with diseases, recommendations and feedbacks about certain medications or medical procedures, and emotional support in the form of encouragement, sympathy, and success stories. Mining this content can prove to be very useful in obtaining crucial insights into community dynamics such as identifying dominant health issues or the effects of social support on community members, identifying influential members, as well as designing smart information retrieval systems for users. In this …

Content truncated to 500 words