The effects of social relationships on management of health behaviors and adoption of positive wellness regimens has been well documented. In the era of digital and participatory health communication, the role of social ties in health promotion has become more complex. Online communities, which digitize peer-to-peer communication, provide a unique opportunity to researchers to understand collective social mechanisms as well as individual factors underlying human behavior change. Most studies of online and offline social networks have not considered the dynamics among communication intent and content with social influence. In the proposed research, we will develop a multi-dimensional methodological framework for social intercourse analysis to leverage the rich and voluminous data provided by online communities. Our framework aims to incorporate and integrate communication intent, semantics and structure of online communication to study sociobehavioral factors of health behaviors and chronic disease management, While our methods will be generally applicable, we will develop them in the context of health-related communication between members of online communities, particularly focusing on smoking cessation and diabetes management. This research proposal will result in- 1) new theoretical frameworks that describe the communication domain in a online social setting for behavior change, 2) scalable techniques to model expressions, semantics, and social dependencies associated self- reported health outcomes, and 3) new proposals for the development of data-driven sociobehavioral interventions to support individuals engaging in positive health behavior changes and chronic disease management.
This project enables retrospective analysis of social intercourse to facilitate our understanding of the associations between communication (content, intent, structure) and social influence dynamics underlying behavior change and chronic disease management as manifested in health-related member communication of online communities. As a component of the proposed research, we will integrate methods of discourse analysis, automated text analysis, and dynamic network models to analyze electronically captured peer-to-peer communication and characterize communication intent and content at scale. By enabling deeper analysis of communication in online platforms, resulting research can help achieve superior personalization of healthy living technologies and campaigns in offline and online formats.
