Automated adaptation of web pages to prove accessibility for people with visual impairments
Year: 2025
Type: dissertation
Abstract: Web accessibility is a fundamental right, yet it remains poorly implemented on many websites. This work developed a Google Chrome extension that uses large language models (LLMs) to automatically fix accessibility issues without altering the original source code. The research follows an applied approach with an experimental design, structured through Design Science Research, and uses Brazilian government websites evaluated by AccessMonitor. Tests showed an improvement in accessibility scores from 6.83 to 7.70, representing a 12.8% increase. The tool successfully corrected elements such as semantic structure, ARIA attributes, and navigation landmarks. The developed solution integrates artificial intelligence and accessibility, offering a practical and scalable solution. It enhances access to digital information for visually impaired users and contributes to technical advancements in the field.
Author: Araujo, Murilo Marçal de
Language: Portuguese
Subfield: Human Factors and Ergonomics
Field: Social Sciences
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W7155457139