RemiHaven: Integrating"In-Town"and"Out-of-Town"Peers to Provide Personalized Reminiscence Support for Older Drifters

2025-03-03

AI Summary

To address loneliness and depression among urban migrant older adults in China (“lao piao zu”) stemming from social isolation and cultural adaptation difficulties, this study proposes a personalized reminiscence support system powered by dual-source peer agents. The method innovatively integrates locally situated and hometown-based peer agents to establish a cross-regional emotional resonance mechanism, shifting reminiscence interventions from static recollection toward dynamic, socially embedded, and context-aware interaction. Leveraging multimodal large language models (MLLMs), the system enables semantic understanding, joint text–image generation, and role-grounded dialogue. Its design was iteratively refined through a two-phase formative study. Empirical evaluation demonstrates significant improvements in reminiscence engagement, affective arousal intensity, and self-identity affirmation. Concurrently, the study identifies critical implementation challenges, including privacy concerns and intergenerational digital divides.

Technology Category

• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Multiagent Systems: Modeling other Agents
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• User Modeling, Personalization and Recommendation: Social recommender systems and personalization for the social Web
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search

Abstract

With increasing social mobility and an aging society, more older adults in China are migrating to new cities, known as"older drifters."Due to fewer social connections and cultural adaptation challenges, they face negative emotions such as loneliness and depression. While reminiscence-based interventions have been used to improve older adults' psychological well-being, challenges such as the lack of tangible materials and limited social resources constrain the feasibility of traditional reminiscence approaches for older drifters. To address this challenge, we designed RemiHaven, a personalized reminiscence support tool based on a two-phase formative study. It integrates"In-Town"and"Out-of-Town"peer agents to enhance personalization, engagement, and emotional resonance in the reminiscence process, powered by Multimodal Large Language Models (MLLMs). Our evaluations show RemiHaven's strengths in supporting reminiscence while identifying potential challenges. We conclude by offering insights for the future design of reminiscence support tools for older migrants.

Problem

• Addressing loneliness and depression in older drifters
• Overcoming lack of tangible materials for reminiscence
• Enhancing reminiscence with personalized peer support

Innovation

• Integrates In-Town and Out-of-Town peer agents
• Uses Multimodal Large Language Models (MLLMs)
• Enhances personalization and emotional resonance