Mining Social Behavior Online: Towards Improved Health and Wellness

Опубликовано 8 августа 2016, 21:31

People are increasingly taking on to social media to share their thoughts and opinions about happenings in daily life. Beyond understanding fundamental aspects of how we act, interact or emote, these platforms provide a promising mechanism to capture behavioral attributes relating to an individual’s social and psychological environment, some of which may signal concerns about their mental health. In this talk, we will examine the harnessing of social media as a tool in behavioral health at multiple scales: individuals, organizations, and populations. Today affective disorders constitute a serious challenge in public health: Depression affects more than 300M people worldwide. First, I will discuss the use of social media, particularly activity, emotion and linguistic expression, in making inferences about behavioral changes in mothers following childbirth. Next, I will present predictive models that leverage social media to detect, ahead of onset, the likelihood of major depression in individuals. Broadly, such predictive forecasting can help develop unobtrusive diagnostic measures of behavioral disorders, and enable wellness tracking in populations in fine-granularity. I will conclude with the potential of this research in the design of next generation privacy-preserving early-warning systems that can bring people timely information and assistance.