ScreenAudit: Detecting Screen Reader Accessibility Errors in Mobile Apps Using Large Language Models

要旨

Many mobile apps are inaccessible, thereby excluding people from their potential benefits. Existing rule-based accessibility checkers aim to mitigate these failures by identifying errors early during development but are constrained in the types of errors they can detect. We present ScreenAudit, an LLM-powered system designed to traverse mobile app screens, extract metadata and transcripts, and identify screen reader accessibility errors overlooked by existing checkers. We recruited six accessibility experts including one screen reader user to evaluate ScreenAudit's reports across 14 unique app screens. Our findings indicate that ScreenAudit achieves an average coverage of 69.2%, compared to only 31.3% with a widely-used accessibility checker. Expert feedback indicated that ScreenAudit delivered higher-quality feedback and addressed more aspects of screen reader accessibility compared to existing checkers, and that ScreenAudit would benefit app developers in real-world settings.

著者
Mingyuan Zhong
University of Washington, Seattle, Washington, United States
Ruolin Chen
University of Washington, Seattle, Washington, United States
Xia Chen
Carnegie Mellon University, Pittsburgh, Pennsylvania, United States
James Fogarty
University of Washington, Seattle, Washington, United States
Jacob O.. Wobbrock
University of Washington, Seattle, Washington, United States
DOI

10.1145/3706598.3713797

論文URL

https://dl.acm.org/doi/10.1145/3706598.3713797

動画

会議: CHI 2025

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2025.acm.org/)

セッション: Vision Accessibility

Annex Hall F203
7 件の発表
2025-04-30 23:10:00
2025-05-01 00:40:00
日本語まとめ
読み込み中…