CodeA11y: Making AI Coding Assistants Useful for Accessible Web Development

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mowar, Peya, Peng, Yi-Hao, Wu, Jason, Steinfeld, Aaron, Bigham, Jeffrey P.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929717712519168
author Mowar, Peya
Peng, Yi-Hao
Wu, Jason
Steinfeld, Aaron
Bigham, Jeffrey P.
author_facet Mowar, Peya
Peng, Yi-Hao
Wu, Jason
Steinfeld, Aaron
Bigham, Jeffrey P.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_10884
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CodeA11y: Making AI Coding Assistants Useful for Accessible Web Development
Mowar, Peya
Peng, Yi-Hao
Wu, Jason
Steinfeld, Aaron
Bigham, Jeffrey P.
Human-Computer Interaction
Software Engineering
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.
title CodeA11y: Making AI Coding Assistants Useful for Accessible Web Development
topic Human-Computer Interaction
Software Engineering
url https://arxiv.org/abs/2502.10884