Chancellor gives keynote at MAISoN 2021 workshop

Assistant Professor Stevie Chancellor gave the opening keynote at the 6th International Workshop on Mining Actionable Insights from Social Networks (MAISoN 2021) - Special Edition on Healthcare Social Analytics on June 7, 2021.

The workshop focused on the use of social media data for building diagnostic, predictive, and prescriptive analysis models for health research and applications such as analyzing how social media can impact people’s physical, mental, and social health, and predicting users' health status and recommending solutions to prevent the risk of committing unfortunate actions, such as suicide.

Chancellor's talk, Human-Centered Machine Learning for Dangerous Mental Health Behaviors Online, discussed her recent research on human-centered machine learning as a lens to make predictions more ethical and compassionate, as well as technically rigorous.

Research and industry both use machine learning 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 propagation 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.

She first talked about her work in machine learning for dangerous mental illness behaviors in online communities, like opioid abuse, suicidal ideation, and promoting eating disorders. Then, she discussed some alarming gaps in data science pipelines for generating labels for training data. She shared how her recent work has found challenges in construct validity that jeopardize the state-of-the-art – and discussed how her research team is attempting to fix this.