Artificial Intelligence (AI) is now at the forefront of technological interest in solving socially challenging problems, like identifying people who may discuss dangerous mental illness behaviors online (e.g. suicidal ideation, self-injury, and opioid addiction). We urgently need better AI to handle the volume and risk of this content in social networks. However, it is important to create AI and interventions in this space that are ethical and helpful, or we risk harming the very people we intend to help.

Assistant Professor Stevie Chancellor will discuss the promises and perils for AI that predicts and intervenes in mental health in social media, and what we can do to make it more technically rigorous, ethical, and compassionate toward people in distress. She will discuss recent work in her research group on TikTok and mental health, and visions for the future of AI to assist in socially hard problems.