Social networks, Facebook and Twitter are continually creating rich repositories of information relating to our activities, emotion and linguistic expression. By leveraging such trails of data and developing machine learning models, we can not only elucidate core aspects of human behavior, but can begin to solve a vista of problems relating to our health behaviors, which have traditionally been challenging.
In this talk I will discuss the harnessing of social media in reasoning about behavioral health concerns experienced by populations around major disruptions in life. In a first study, I will present analyses and computational models that make automated inferences about the status and dynamics of postpartum depression in new mothers via postings made on Twitter and Facebook. In a second study, we will examine the affective responses in Twitter experienced by communities in Mexico embroiled in protracted armed conflict and how they might indicate desensitization to violence. Broadly, I will discuss how this new line of research bears potential in informing the design of early-warning systems and interventions to help individuals and policymakers be more proactive about health and wellbeing.\\
Munmun De Choudhury is currently an assistant professor at the School of Interactive Computing, Georgia Tech. Munmun’s research interests are in computational social science, with a specific focus on reasoning about our health behaviors from social digital footprints. She has been a recipient of the Grace Hopper Scholarship, recognized with an IBM Emergent Leaders in Multimedia award, and recipient of ACM SIGCHI 2014 best paper award and ACM SIGCHI honorable mention awards in 2012 and 2013. Earlier, Munmun was a postdoctoral researcher at Microsoft Research, a research fellow at Rutgers, and obtained a PhD in Computer Science from Arizona State University in 2011.