Learning from Elders: Making an LLM-powered Chatbot for Retirement Communities more Accessible through User-centered Design

2025-04-11

AI Summary

Older adults in retirement communities face significant barriers in adopting digital health tools due to low digital and eHealth literacy. Method: This study proposes a dual-function large language model (LLM) chatbot framework specifically designed for older users, integrating persona-driven needs analysis, an adjustable interface (e.g., scalable fonts and themes), personalized follow-up questioning, and concise prompt engineering. The system—built on GPT-3.5 Turbo and Streamlit—supports responsive text- and voice-based interaction, with speech-to-text integration underway. Contribution/Results: Pilot deployment demonstrated substantial improvements in user satisfaction, perceived usability, and information retrieval efficiency; reduced operational complexity; and increased willingness to engage with technology. To our knowledge, this is the first work to systematically unify gerontological design principles with LLM capabilities, offering a reproducible methodology and practical implementation model for sustainable digital inclusion interventions.

Technology Category

• Humans and AI: AI for Accessibility
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Low technology and eHealth literacy among older adults in retirement communities hinder engagement with digital tools. To address this, we designed an LLM-powered chatbot prototype using a human-centered approach for a local retirement community. Through interviews and persona development, we prioritized accessibility and dual functionality: simplifying internal information retrieval and improving technology and eHealth literacy. A pilot trial with residents demonstrated high satisfaction and ease of use, but also identified areas for further improvement. Based on the feedback, we refined the chatbot using GPT-3.5 Turbo and Streamlit. The chatbot employs tailored prompt engineering to deliver concise responses. Accessible features like adjustable font size, interface theme and personalized follow-up responses were implemented. Future steps include enabling voice-to-text function and longitudinal intervention studies. Together, our results highlight the potential of LLM-driven chatbots to empower older adults through accessible, personalized interactions, bridging literacy gaps in retirement communities.

Problem

• Enhancing digital tool accessibility for low-literacy older adults
• Designing user-centered LLM chatbot for retirement communities
• Bridging technology and eHealth literacy gaps via AI

Innovation

• Human-centered design for elderly accessibility
• GPT-3.5 Turbo with tailored prompt engineering
• Adjustable font size and interface themes