The Impact of Virtually Crowdsourced Social Support on Individual Health: Analyzing Big Datasets for Underlying Causalities
With the rise of online health communities, patients or consumers are using these communities to exchange support through enhanced social relations and interpersonal transactions. An emerging and interesting area of research is to comprehensively understand the interaction dynamics within online health communities. The current study examined the impact of virtually crowdsourced social support on individual health via analyses of big health data. Based on previous research, we propose a conceptual framework of social relations in the context of online health communities and test it through a quantitative field study. Specifically, text mining techniques are utilized to automate the content analysis of big health data. Contributions of this research will not only extend current understanding of social influence in online health communities, but also shed light on the general approach of coping with big datasets in research as well as the design and management of online health communities.
Chen, L., & Straub, D. W. (2015). The Impact of Virtually Crowdsourced Social Support on Individual Health: Analyzing Big Datasets for Underlying Causalities. Proceedings of the 2015 Americas Conference on Information Systems (2015, Fajardo, Puerto Rico).
21st Americas Conference on Information Systems, AMCIS 2015 (2015: Aug. 13-15, Fajardo, Puerto Rico)
Business and Information Technology
Keywords and Phrases
Automatic content analysis; Big data; Health crowd; Latent dirichlet allocation (LDA); Online health communities; Social support; Support vector machine (SVM); Text mining; Unified medical language system (UMLS)
International Standard Book Number (ISBN)
Article - Conference proceedings
© 2015 Association for Information Systems (AIS), All rights reserved.