CMU logo
Expand Menu
Close Menu

HCII Seminar Series - Stevie Chancellor

Stevie Chancellor

Stevie Chancellor
Assistant Professor in the Department of Computer Science & Engineering at the University of Minnesota


Newell-Simon Hall 1305

Video link


"Human-centered Machine Learning for Dangerous Mental Illness Behaviors Online"

Research and industry both use machine learning (ML) to identify and intervene in physically dangerous health behaviors discussed on social media, such as advocating for self-injury or violence. There is an urgent need to innovate data-driven systems to handle the volume and risk of this content in social networks and its contagion to others in the community. However, traditional approaches to prediction have mixed success, in part because technical solutions oversimplify complex behavior and the unique interactions of communities with both individuals and platforms.

In this talk, I will discuss the importance of human-centered machine learning as a lens to make these predictions more ethical and compassionate, as well as technically rigorous. I’ll talk about my work in ML for dangerous mental illness behaviors in online communities, like opioid abuse, suicidal ideation, and promoting eating disorders. Then, I’ll discuss some alarming gaps in the validity of data science pipelines for generating labels for training data that jeopardize the state-of-the-art - and I’ll discuss how we’re attempting to fix this. I will also discuss our work using recent human-centered methods like interviews to understand peoples’ needs for ML deployment for mental health. Together, these inform an agenda for human-centered machine learning that is scientifically and technically rich and more considerate of social contexts in data.

Speaker's Bio

Dr. Stevie Chancellor is an Assistant Professor in the Department of Computer Science & Engineering at the University of Minnesota. Her research combines approaches from HCI and ML to build and critically evaluate human-centered systems, focusing on high-risk health behaviors in online communities. Her work has been recognized with awards from CHI, CSCW, and ICWSM, and she has published in venues such as nature partner journal digital medicine, JMIR – Mental Health, and New Media and Society, and has been covered in international outlets, such as the United Nations ITU, The New York Times, The Washington Post, The Atlantic, and other popular press. Dr. Chancellor received her doctorate in Human-Centered Computing from Georgia Tech and completed a CS+X Postdoctoral Fellowship at Northwestern University.

Speaker's Website