Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Exploring the Design of Generative AI in Supporting Music-based Reminiscence for Older Adults

Yucheng Jin, Wanling Cai, Li Chen, Yizhe Zhang, Gavin Doherty, Tonglin Jiang

TL;DR

This paper investigates how generative AI can support music-based reminiscence for older adults through a user-centered design process. It combines interviews with social workers and two design workshops with older adults, using a video prototype (AI-DJ) and a digital prototype (MusicJourney) to elicit attitudes, preferences, and design implications. The study finds that AI-generated conversations and images can enhance reminiscence when personalized, authentic, and delivered with user control, but raises concerns about tone, content relevance, privacy, and group sharing dynamics. The contributions provide concrete design considerations for future AI reminiscence tools, highlighting mixed-initiative interaction, adaptive multimodal input, and trust-building as key factors for adoption and well-being in older adult populations.

Abstract

Music-based reminiscence has the potential to positively impact the psychological well-being of older adults. However, the aging process and physiological changes, such as memory decline and limited verbal communication, may impede the ability of older adults to recall their memories and life experiences. Given the advanced capabilities of generative artificial intelligence (AI) systems, such as generated conversations and images, and their potential to facilitate the reminiscing process, this study aims to explore the design of generative AI to support music-based reminiscence in older adults. This study follows a user-centered design approach incorporating various stages, including detailed interviews with two social workers and two design workshops (involving ten older adults). Our work contributes to an in-depth understanding of older adults' attitudes toward utilizing generative AI for supporting music-based reminiscence and identifies concrete design considerations for the future design of generative AI to enhance the reminiscence experience of older adults.

Exploring the Design of Generative AI in Supporting Music-based Reminiscence for Older Adults

TL;DR

This paper investigates how generative AI can support music-based reminiscence for older adults through a user-centered design process. It combines interviews with social workers and two design workshops with older adults, using a video prototype (AI-DJ) and a digital prototype (MusicJourney) to elicit attitudes, preferences, and design implications. The study finds that AI-generated conversations and images can enhance reminiscence when personalized, authentic, and delivered with user control, but raises concerns about tone, content relevance, privacy, and group sharing dynamics. The contributions provide concrete design considerations for future AI reminiscence tools, highlighting mixed-initiative interaction, adaptive multimodal input, and trust-building as key factors for adoption and well-being in older adult populations.

Abstract

Music-based reminiscence has the potential to positively impact the psychological well-being of older adults. However, the aging process and physiological changes, such as memory decline and limited verbal communication, may impede the ability of older adults to recall their memories and life experiences. Given the advanced capabilities of generative artificial intelligence (AI) systems, such as generated conversations and images, and their potential to facilitate the reminiscing process, this study aims to explore the design of generative AI to support music-based reminiscence in older adults. This study follows a user-centered design approach incorporating various stages, including detailed interviews with two social workers and two design workshops (involving ten older adults). Our work contributes to an in-depth understanding of older adults' attitudes toward utilizing generative AI for supporting music-based reminiscence and identifies concrete design considerations for the future design of generative AI to enhance the reminiscence experience of older adults.
Paper Structure (41 sections, 6 figures, 1 table)

This paper contains 41 sections, 6 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Benefits of Reminiscence for Older Adults
  4. Technology for Reminiscence
  5. Generative AI
  6. Method
  7. Preparation Work
  8. Participants
  9. Workshop I: Understanding Older Adults
  10. Workshop II: Examining Design Considerations
  11. Data Collection and Analysis
  12. Positionality Statements
  13. Ethical Considerations
  14. In-Depth Understanding of Older Adults
  15. Perspectives on Generated Conversations
  16. ...and 26 more sections

Figures (6)

  • Figure 1: Overall research design and procedure.
  • Figure 2: The overview of Workshop I including various activities ranging from explaining generative AI and video prototype demonstration to group design discussion.
  • Figure 3: The screenshots of the video prototype (AI-DJ) used in Workshop I. (1) AI-DJ generated images based on lyrics in the individual setting. (2) AI-DJ generated images based on other listeners' comments in the group setting.
  • Figure 4: The design activities conducted in the two design workshops. In Workshop I: (1) the participants discussed the design concept represented by the video prototype in a semi-structured group interview; (2) the participants generated new design ideas through collective brainstorming. In Workshop II: (3) the participants interacted with the digital prototype (MusicJourney); (4) the participants gave feedback on design alternatives for interacting with the generated images in conversation.
  • Figure 5: The overview of Workshop II including various activities, such as introducing and testing digital prototypes and group design discussion.
  • ...and 1 more figures