CodeA11y: Making AI Coding Assistants Useful for Accessible Web Development

要旨

A persistent challenge in accessible computing is ensuring developers produce web UI code that supports assistive technologies. Despite numerous specialized accessibility tools, novice developers often remain unaware of them, leading to ~96% of web pages that contain accessibility violations. AI coding assistants, such as GitHub Copilot, could offer potential by generating accessibility-compliant code, but their impact remains uncertain. Our formative study with 16 developers without accessibility training revealed three key issues in AI-assisted coding: failure to prompt AI for accessibility, omitting crucial manual steps like replacing placeholder attributes, and the inability to verify compliance. To address these issues, we developed CodeA11y, a GitHub Copilot Extension, that suggests accessibility-compliant code and displays manual validation reminders. We evaluated it through a controlled study with another 20 novice developers. Our findings demonstrate its effectiveness in guiding novice developers by reinforcing accessibility practices throughout interactions, representing a significant step towards integrating accessibility into AI coding assistants.

著者
Peya Mowar
Carnegie Mellon University, Pittsburgh, Pennsylvania, United States
Yi-Hao Peng
Carnegie Mellon University, Pittsburgh, Pennsylvania, United States
Jason Wu
Apple, Seattle, Washington, United States
Aaron Steinfeld
Carnegie Mellon University, Pittsburgh, Pennsylvania, United States
Jeffrey P. Bigham
Carnegie Mellon University, Pittsburgh, Pennsylvania, United States
DOI

10.1145/3706598.3713335

論文URL

https://dl.acm.org/doi/10.1145/3706598.3713335

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: Accessibility 2

Annex Hall F206
7 件の発表
2025-05-01 01:20:00
2025-05-01 02:50:00
日本語まとめ
読み込み中…