Can AI Assess Web Accessibility in Multilingual Content? A Study of Romanian Universities’ Localised Websites

Diplôme Master Can AI Assess Web Accessibility in Multilingual Content? A Study of Romanian Universities’ Localised Websites eng 2024 author Sandu Emanuela 987685 director Rodriguez Vazquez Silvia 0000-0002-9945-5544 722101 Département de traitement informatique multilingue (TINFM) This study evaluates the accessibility of multilingual websites of public universities in Romania. University websites play a central role for the academic community, and inaccessible content can exclude individuals with disabilities from participating in educational, professional, or social activities. The analysis focused on 32 homepages, considering English and French localised versions, with particular attention to the needs of visually impaired users. To assess web accessibility compliance with Web Content Accessibility Guidelines 2.1, we performed two tests: an automated evaluation to identify common language-related errors, and a complementary analysis using ChatGPT to examine the identified errors that typically require manual verification. Findings confirmed that the multilingual content on the tested university websites contains many language-related barriers. The AI-based evaluation proved effective when compared to manual assessment, as ChatGPT evaluated errors such as untranslated or redundant alternative text, mismatches between link descriptions and their purpose, untranslated page titles, or incorrect language declarations in 75% of cases. Positive outcomes suggest that this preliminary study could serve as a foundation for further research into the intersection of localisation, web accessibility, and artificial intelligence, moving beyond controlled tests. Web Localisation Multilingual Web Web accessibility WCAG 2.1 Automatic Evaluation AI technologies ChatGPT Dewey 418.02 Maîtrise universitaire en traduction et technologies 111 Département de traduction 91 false 3e389191-e32c-41dc-aba5-22de4688edce Master thesis Public SanduEmanuela_Memoire-clean.pdf 2502761 application/pdf 52aaf48d02731a63d8eedd82dd1643780fbb029a23b9c4a2f5ae17adb5a9daec openAccess Faculté de traduction et d'interprétation / Département de traduction

Title	Published in	Access level	OA Policy	Year	Views	Downloads

Can AI Assess Web Accessibility in Multilingual Content? A Study of Romanian Universities’ Localised Websites				2024	114	270

Archive ouverte UNIGE

Sandu, Emanuela

account_balance UNIGE affiliation entities

UNIGE affiliation entities