Title: Designing Assistive and Explainable AI Systems for Older Adults Aging in Place

Niharika Mathur 

Ph.D. Student in Human-Centered Computing (HCC) 

School of Interactive Computing 

Georgia Institute of Technology 

Date: Tuesday, May 13th, 2025
Time: 3-5 pm EST 

Location: CODA C1015 or Join via Zoom

Committee 

Dr. Elizabeth Mynatt (Advisor) - Khoury College of Computer Sciences, Northeastern University

Dr. Sonia Chernova (Co-advisor) - School of Interactive Computing, Georgia Institute of Technology

Dr. Thomas Ploetz - School of Interactive Computing, Georgia Institute of Technology

Dr. Mark Riedl - School of Interactive Computing, Georgia Institute of Technology

Dr. Jodi Forlizzi - School of Computer Science and HCII, Carnegie Mellon University

Dr. James Landay, School of Engineering and Institute for Human-Centered AI, Stanford University

Abstract

This dissertation conducts a human-centered examination of the challenges and opportunities for designing assistive AI systems for older adults. Motivated by the growing population of older adults requiring trustworthy technological support as they age in place, this dissertation investigates the challenges that older adults face while interacting with AI systems, including frequent conversational breakdowns and lack of contextual explanations. Through a multi-stage research process involving participatory design with older adults and a longitudinal field deployment, this dissertation develops a human-centered design framework for generating AI explanations that are tailored to older adults’ goals and motivations. This framework leverages the diverse information sources present in a user's sociotechnical environment and offers ways to generate contextually grounded and personalized explanations. The proposed work for this dissertation discusses a field deployment study to incorporate this framework into an LLM-based Conversational AI system for older adults in an assisted living facility. Through presenting evidence-based insights on older adults’ interactions with AI systems and a generative design framework, this dissertation contributes to the fields of Human-Centered Computing, Human-Centered Explainable AI, and assistive technologies for aging populations.