ABSTRACT
The use of automated accessibility testing tools remains a common practice for evaluating web accessibility. However, the results obtained from these tools may not always provide a comprehensive and complete view of a site's accessibility status. The main purpose of this study is to improve web accessibility by automatically remediating non-accessible ones using Large Language Models (LLM), particularly ChatGPT. The effectiveness of the used model in detecting and remediating accessibility issues to ensure compliance with the Web Content Accessibility Guidelines (WCAG 2.1) is also discussed. By using ChatGPT as a remediation tool, this study investigates the potential of LLM in improving web accessibility. In the case study, two websites that did not adhere to the WCAG 2.1 guidelines were selected as the primary experimental subjects for the study. These websites were assessed using the web accessibility evaluation tool, WAVE, to detect accessibility issues. The identified issues served then as the basis for remediation using ChatGPT. The effectiveness of the used advanced language model as a web accessibility remediation tool was evaluated by comparing its findings with those obtained from manual accessibility testing. The results of this comparison have significant implications for stakeholders involved in achieving WCAG compliance and contribute to the development of more accessible online platforms for individuals with disabilities.
- I. Abu Doush, K. Sultan, M. A. Al-Betar, Z. Almeraj, Z. A. A. Alyasseri, and M. A. Awadallah, “Web accessibility automatic evaluation tools: to what extent can they be automated?,” CCF Trans. Pervasive Comp. Interact., Mar. 2023, doi: 10.1007/s42486-023-00127-8.Google ScholarCross Ref
- P. Brophy and J. Craven, “Web accessibility,” Library trends, vol. 55, no. 4, pp. 950–972, 2007.Google ScholarCross Ref
- Web Content Accessibility Guidelines (WCAG) 2.1. https://www.w3.org/TR/WCAG21/ (accessed Mar. 15, 2023).Google Scholar
- H. Y. Abuaddous, M. Z. Jali, and N. Basir, “Web accessibility challenges,” International Journal of Advanced Computer Science and Applications (IJACSA), 2016.Google ScholarCross Ref
- A. Othman, A. Al Mutawaa, A. Al Tamimi, and M. Al Mansouri, “Assessing the Readiness of Government and Semi-Government Institutions in Qatar for Inclusive and Sustainable ICT Accessibility: Introducing the MARSAD Tool,” Sustainability, vol. 15, no. 4, p. 3853, 2023.Google ScholarCross Ref
- A. N. Al Jabor, F. Adnan, M. Park, and A. Othman, “Mada Web Accessibility Monitor Tool,” in 2021 8th International Conference on ICT & Accessibility (ICTA), Dec. 2021, pp. 1–5. doi: 10.1109/ICTA54582.2021.9809423.Google ScholarCross Ref
- “Introducing ChatGPT.” https://openai.com/blog/chatgpt (accessed Mar. 15, 2023).Google Scholar
- “WAVE Web Accessibility Evaluation Tools.” https://wave.webaim.org/ (accessed Mar. 15, 2023).Google Scholar
- Y. Yesilada, G. Brajnik, M. Vigo, and S. Harper, “Understanding web accessibility and its drivers,” in Proceedings of the cross-disciplinary conference on web accessibility, 2012, pp. 1–9.Google ScholarDigital Library
- M. Paris, “Website accessibility: a survey of local e-government websites and legislation in Northern Ireland,” Universal access in the information society, vol. 4, pp. 292–299, 2006.Google ScholarDigital Library
- J. T. Richards and V. L. Hanson, “Web accessibility: a broader view,” in Proceedings of the 13th international conference on World Wide Web, 2004, pp. 72–79.Google ScholarDigital Library
- J. Kuzma, D. Yen, and K. Oestreicher, “Global e-government web accessibility: an empirical examination of EU, Asian and African sites,” 2009.Google Scholar
- J. Lazar, A. Dudley-Sponaugle, and K.-D. Greenidge, “Improving web accessibility: a study of webmaster perceptions,” Computers in human behavior, vol. 20, no. 2, pp. 269–288, 2004.Google ScholarCross Ref
- D. Baidoo-Anu and L. Owusu Ansah, “Education in the Era of Generative Artificial Intelligence (AI): Understanding the Potential Benefits of ChatGPT in Promoting Teaching and Learning,” Available at SSRN 4337484, 2023.Google Scholar
- “Qatar Airways.” https://www.qatarairways.com/ (accessed Mar. 19, 2023).Google Scholar
- “British Airways.” https://www.britishairways.com/ (accessed Mar. 19, 2023).Google Scholar
- A. Dhouib, C. Kolski, and M. Neji, “Towards a Web-based Multi-Criteria Decision Support System for the Layered Evaluation of Interactive Adaptive Systems,” Universal Access in the Information Society, Nov. 2021, doi: 10.1007/s10209-021-00850-y.Google ScholarDigital Library
Index Terms
- Fostering websites accessibility: A case study on the use of the Large Language Models ChatGPT for automatic remediation
Recommendations
Cognitive-based approach for assessing accessibility of e-government websites
UAHCI'13: Proceedings of the 7th international conference on Universal Access in Human-Computer Interaction: user and context diversity - Volume 2The importance of internet and other communication technologies play a vital role in modern life. Websites are inherently designed for a targeted group of users, normal sighted or for the whole population including those who are visually impaired. Blind ...
Investigating the applicability of accessibility standards for disabled person on educational websites
ECC'11: Proceedings of the 5th European conference on European computing conferenceThis paper exposes an approach to investigate accessible contents of educational websites to insure and measure its compliance with accessibility standards for visually impaired people. The W3C Web Accessibility Initiative (WAI) has been established to ...
A Pilot Study of Collaborative Accessibility: How Blind People Find an Entrance
MobileHCI '15: Proceedings of the 17th International Conference on Human-Computer Interaction with Mobile Devices and ServicesDue to inaccurate GPS data and complex environment close to buildings, for blind people it is often hard to find entrances in unknown areas. In this paper, we propose an enhance method that combines crowd-sourcing technology and location-based services, ...
Comments