FFCEP Presentation: Sayde King, Doctoral Candidate, Department of Computer Science and Engineering, University of South Florida
Abstract: AI for Mental Health: A Focus on Behavior and Deception In this talk, King explores applied artificial intelligence in mental health contexts. Summarizing three research projects, she: (1) details the disclosure-based self-stigma reduction program, Up To Me, which was developed to increase inclusion and engagement of people with mental illness on college campuses by teaching strategies to weigh costs and benefits of disclosing one’s mental illness. Further, King elaborates on the program’s evaluation mechanisms, which involve both self-reported and passively recorded smartphone sensor data. The latter reflects a unique merging of behavioral and computer sciences that serves to facilitate behavioral modeling using artificial intelligence as an objective measure of Up to Me outcomes. (2) unpacks qualitative interview data from twenty mental health professionals characterizing the present landscape of client deception with respect to clinician-client collaboration via five key elements and eliciting their perspectives on critical considerations regarding the potential deployment of AI for real-time deception detection during therapeutic sessions. (3) unveils the saliency of facial, affective, eye gaze, and body gesture features for deception detection across four distinct domains: biography, academics, mental health, and crime/forensics. Leveraging four hundred video recordings from two datasets, King aims to identify key indicators of deception within these domains and assess which indicators persist across different contexts. Our findings indicate that while certain features, such as face and gesture, are particularly effective in specific domains (e.g., crime/forensics), other indicators, such as facial movements and eye gaze, consistently emerge as significant cues across multiple domains, including biographical and mental health contexts.
Bio: Sayde King is a Ph.D. candidate in the Department of Computer Science and Engineering at the University of South Florida. She also received her MS and BS in computer science from the University of South Florida in 2022, and 2019, respectively. King is a member of the Cyber Identity and Behavior Research Laboratory, which studies biometric systems, smart sensing for human behavior analyses, and applied natural language processing. Her current research explores automated deception detection for nonengineering applications. King is a firm believer in user-centered design and aims to involve stakeholders throughout the design process—including the discussion surrounding whether the technology is needed in the first place. She employs a range of qualitative methods accompanied by applying artificial intelligence in empirical investigations. King has actively contributed to the academic community by serving as a program committee member for workshops at renowned conferences such as the IEEE International Conference on Automatic Face and Gesture Recognition and the IEEE/IAPR International Conference on Pattern Recognition. She is a Florida Education Fund McKnight Dissertation Fellow, Alfred P. Sloan Foundation Minority Ph.D. Scholar, and a National GEM Consortium Employer Fellow, sponsored by the MIT Lincoln Laboratory.
Meeting URL: https://rit.zoom.us/j/97864104509?from=addon
Meeting ID: 978 6410 4509
Event Snapshot
When and Where
Who
Open to the Public
Interpreter Requested?
No