In this talk, we will examine the harnessing of social networks and media as a tool in behavioral health. Today affective disorders constitute a serious challenge in personal and public health, with most of them being statistically under-reported. More than 9% of US population is known to suffer from depression.
I will present a range of problems where social media can help us understand behavior at multiple scales: individuals, organizations, and larger populations. Through the analysis of online activity, emotion and linguistic expression, I will discuss how behavioral health concerns can be identified in each of the three contexts. Particularly, I will discuss the use of social media in making inferences about behavioral changes in new mothers following childbirth. Broadly, such predictive forecasting can help develop unobtrusive diagnostic measures of behavioral disorders, such as postpartum depression, elderly, or manic depression, and can even complement clinical diagnosis methodologies in the future.
I will conclude with the potential of this line of research in informing the design of next generation low-cost, privacy-sensitive early-warning systems and interventions. These tools could bring people timely information and assistance, and thereby help improve their quality of life.
Bio: Munmun De Choudhury is a postdoctoral researcher at Microsoft Research, Redmond. Her research interests are in computational social science. By combining machine learning, human computer interaction, and social science, Munmunís research attempts to decipher human behavior, as manifested in peopleís online activities. She has been a recipient of the Grace Hopper Scholarship, a finalist of Facebook Fellowship, and winner of two Best Paper Honorable Mention awards from ACM SIGCHI. Earlier, Munmun was a research fellow at Rutgers University, and obtained a PhD in Computer Science from Arizona State University in 2011.