Author ORCID Identifier

https://orcid.org/0000-0003-0755-6039

Date of Award

2026

Document Type

Thesis (Ph.D.)

Department or Program

Engineering Sciences

First Advisor

Elizabeth Murnane

Abstract

This thesis addresses a gap in the human-computer interaction literature regarding the design, development, and evaluation of narrative-based AI assistance for collaborative, complex problem solving. I explore this design space through three case studies across the domains of education and dementia care. This work encompasses multi-year industry partnerships and longitudinal fieldwork, user-centered design, dataset curation, model training, and system evaluation.

Specifically, the first case study considers a story-based web platform for teaching AI literacy through peer-generated, personalized narrative scaffolding. Learners on the platform showed significant knowledge gains and other learning-related outcomes. To describe the novel design of this system, I introduce the concept of narrative-based learnersourcing.

The second and third studies consider introducing AI assistance into under-resourced long-term care facilities to help caregivers provide better-quality care to residents living with dementia. Through a person-centered care approach, I show how an AI system can assist in observing and sharing relevant narrative-based care insights, such as musical interventions, pertinent life history, and uncovered preferences. Following the collection of a custom training dataset, I deployed CareInsights, an intervention that provides caregivers with real-time, chat-based support in the form of context-appropriate, narrative-form descriptions extracted from aggregated video, text, and integrated electronic health records data. I later extended this work, in the third study, to consider a broader range of interface designs and data sharing between families and staff. Across the two care studies, findings indicated outcomes consistent with more effective person-centered dementia care, deepened family involvement in care, and no significant change in measured workload. These studies also surfaced inherent tensions around automation, oversight, and privacy.

In the Discussion, I analyze these case studies' empirical findings through the theoretical lens of sensemaking, which describes the interpretive processes—involving individual cognition and social interaction—through which people organize ambiguous circumstances into actionable narratives. Bridging theory and practice, I conclude by introducing a novel design framework called Collaborative Narrative Scaffolding to guide the design of future AI assistance for complex problem solving in real-world, collaborative settings such as these.

Original Citation

This thesis includes work from the following published papers:

Dylan Edward Moore, Sophia R. R. Moore, Bansharee Ireen, Winston P. Iskandar, Grigory Artazyan, and Elizabeth L. Murnane. 2024. Teaching artificial intelligence in extracurricular contexts through narrative-based learnersourcing. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems (CHI '24). Association for Computing Machinery, New York, NY, USA, Article 270, 1–28. https://doi.org/10.1145/3613904.3642198  

Dylan Edward Moore, Songyun Tao, Sophia R.R. Moore, Brian Morgan, Dio Tadin, Christina Sapp Tadin, and Elizabeth L. Murnane. 2025. CareInsights: AI-enabled Infrastructure for Person-centered Dementia Care in Resource-constrained Facilities. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 9, 4, Article 202 (December 2025), 42 pages. https://doi.org/10.1145/3770687  

Dylan Edward Moore, Songyun Tao, Emma Ricci-De Lucca, Christina Sapp Tadin, Dio Tadin, Brian Morgan, and Elizabeth L. Murnane. 2025. Family In The Loop: Enabling Family Involvement and Person-Centered Dementia Care at Long-Term Care Facilities with Collaborative AI Tools. Proc. ACM Hum.-Comput. Interact. 9, 7, Article CSCW418 (November 2025), 45 pages. https://doi.org/10.1145/3757599

Download

Share

COinS