Situated Understanding of Errors in Older Adults' Interactions with Voice Assistants: A Month-Long, In-Home Study

TL;DR

This study investigates older adults' interactions with voice assistants over a month, analyzing errors and exploring how large language models like ChatGPT can improve error handling and user experience.

Contribution

It introduces a novel in-home data collection method and evaluates LLMs' potential to enhance error management in voice assistants for older users.

Findings

In-the-wild audio data reveals common interaction errors.

ChatGPT-powered VA shows promise in error handling.

Design considerations improve VA alignment with older adults' needs.

Abstract

Our work addresses the challenges older adults face with commercial Voice Assistants (VAs), notably in conversation breakdowns and error handling. Traditional methods of collecting user experiences-usage logs and post-hoc interviews-do not fully capture the intricacies of older adults' interactions with VAs, particularly regarding their reactions to errors. To bridge this gap, we equipped 15 older adults' homes with smart speakers integrated with custom audio recorders to collect "in-the-wild" audio interaction data for detailed error analysis. Recognizing the conversational limitations of current VAs, our study also explored the capabilities of Large Language Models (LLMs) to handle natural and imperfect text for improving VAs. Midway through our study, we deployed ChatGPT-powered VA to investigate its efficacy for older adults. Our research suggests leveraging vocal and verbal responses combined with LLMs' contextual capabilities for enhanced error prevention and management in VAs, while proposing design considerations to align VA capabilities with older adults' expectations.