Title: Understanding Social Requirements for Social Media Powered Artificial Intelligence (SoMPAI) for Mental Health Care 

Date: Tuesday, June 20th, 2023 

Time: 12:00 PM – 3:00 PM Eastern Time 

Location: Zoom Meeting (https://gatech.zoom.us/j/96421869303) 

Dong Whi Yoo 

Ph.D. Candidate in Human-Centered Computing 

School of Interactive Computing 

Georgia Institute of Technology 

Committee: 

Dr. Munmun De Choudhury (co-advisor), School of Interactive Computing, Georgia Institute of Technology

Dr. Gregory D. Abowd (co-advisor), School of Interactive Computing, Georgia Institute of Technology & College of Engineering, Northeastern University 

Dr. Andrea Grimes Parker, School of Interactive Computing, Georgia Institute of Technology 

Dr. Jennifer Gahee Kim, School of Interactive Computing, Georgia Institute of Technology 

Dr. Mary Czerwinski, Human Understanding and Empathy group, Microsoft Research, Redmond 

Dr. Madhu Reddy, Donald Bren School of Information and Computer Sciences, University of California, Irvine 

Abstract: 

Mental health poses unique challenges in the field of medicine, as it heavily relies on patients' abilities to express their cognitive and emotional states, symptom progression, and interpersonal relationships. This reliance often leads to less effective evaluations and treatments. Recent advancements in artificial intelligence (AI) have emerged as a promising avenue for developing more objective criteria in mental health care. However, despite extensive efforts from interdisciplinary researchers in computer science, mental health, and related fields, the successful integration of AI into real-world mental health contexts remains elusive. 

This dissertation addresses this critical gap between AI research and mental health practice by exploring the social requirements of AI technologies for mental health care from the perspectives of patients and clinicians. Building on the emerging field of Human-AI Interaction, this research investigates the specific needs and expectations of end-users, emphasizing a human-centered design approach. Through close collaboration with clinicians and patients, this study aims to uncover the essential considerations, expectations, and concerns surrounding the use of AI models in mental health care. 

The dissertation contributes to multiple domains. Firstly, it expands the concept of social requirements and the socio-technical gap in Computer-Supported Cooperative Work (CSCW) within the context of mental health AI technologies. By examining the perspectives of mental health patients and clinicians, it provides empirical evidence that informs recent research in Human-AI Interaction. Moreover, the design implications derived from this dissertation will facilitate the development of implementable AI technologies that can effectively support and enhance current mental health practices.