Bridging the Cognitive Gap: Co-Designing and Evaluating a Voice-Enabled Community Chatbot for Older Adults

2026-03-11

AI Summary

This study addresses the tendency of older adults in senior living communities to avoid digital portals due to physical and cognitive impairments. To mitigate this, the authors propose a “glass-box” approach that integrates AI transparency with age-inclusive design principles. Through co-design sessions and AI literacy workshops, they deployed a voice-driven, multimodal large language model chatbot within a retirement community. The system significantly enhanced users’ technological understanding (p = 0.004) and perceived transparency (p = 0.001), shifting reliance from blind trust toward evidence-based, rational engagement. However, usability markedly declined among users aged 80 and above (r = −0.50), underscoring the critical need for zero-touch interaction paradigms tailored to the oldest-old population.

Technology Category

• Humans and AI: AI for Accessibility
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness

Application Category

• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Responsible Web: Algorithmic accountability and transparency on the web
• Security and Privacy: Data transparency and provenance

Abstract

Digital portals in retirement communities often create physical and cognitive barriers for older adults, leading to digital avoidance. Generative AI offers a solution by enabling natural language interaction, yet its adoption is hindered by the opaque, "Black Box" nature of these systems and lingering usability challenges. To address this, we evaluated a voice-enabled Large Language Model (LLM) chatbot at a continuing care retirement community in the Pacific Northwest. Through a mixed-methods Co-Design and Literacy Workshop (N=25), we applied a "Glass Box" approach combining multimodal accessibility with intentional AI education. The intervention significantly improved participants' technical understanding (p=0.004) and perceived transparency (p=0.001), shifting their interaction model from blind trust to informed reliance prioritizing verifiable evidence. While voice input reduced cognitive load, usability scores dropped significantly for users aged 80 and older (r=-0.50), indicating that truly age-inclusive AI must evolve beyond touch-based interfaces toward zero-touch navigation.

Problem

• digital divide
• older adults
• voice-enabled chatbot
• cognitive barriers
• age-inclusive AI

Innovation

• Voice-enabled LLM
• Glass Box AI
• Co-Design
• AI Literacy
• Age-inclusive Interaction