Computational Methods to Understand Online Deviant Mental Health Behaviors

Faculty: 
Munmun De Choudhury
Students: 
Stevie Chancellor

Social media has changed how individuals cope with health challenges in good and bad ways. Especially for stigmatized mental health conditions like depression, groups and communities offer positive outcomes for those suffering from mental illness. However, in some mental health communities, individuals promote deliberate self-injury, disordered eating habits, and suicidal ideas as acceptable choices rather than dangerous actions. These communities pose problems for the individuals in them, others who interact with this content, social networks who moderate this information, and broader stakeholders like clinicians.

My research investigates online deviant mental health communities with computational social science techniques at-scale, focusing on the pro-eating disorder community. Using large-scale social media datasets and techniques like machine learning and statistical modeling, I analyze and understand patterns of deviant behavior, these community's connections to mental health and support, and platform ethics in dealing with this behavior. I'll discuss the novel methodologies and pipelines I've innovated to understand these behaviors on social media sites, my current work, and how this work can help doctors and clinicians and social networks better facilitate healthier interactions on these platforms.

Lab: 
Director: 
Munmun De Choudhury
Faculty: 
Munmun De Choudhury

The SocWeB Lab's mission is to develop novel computational techniques, and technologies powered by these techniques, to responsibly and ethically employ social media in quantifying, understanding, and improving our mental health and well-being.