Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

ACCESS: Prompt Engineering for Automated Web Accessibility Violation Corrections (2401.16450v2)

Published 28 Jan 2024 in cs.HC, cs.AI, and cs.SE

Abstract: With the increasing need for inclusive and user-friendly technology, web accessibility is crucial to ensuring equal access to online content for individuals with disabilities, including visual, auditory, cognitive, or motor impairments. Despite the existence of accessibility guidelines and standards such as Web Content Accessibility Guidelines (WCAG) and the Web Accessibility Initiative (W3C), over 90% of websites still fail to meet the necessary accessibility requirements. For web users with disabilities, there exists a need for a tool to automatically fix web page accessibility errors. While research has demonstrated methods to find and target accessibility errors, no research has focused on effectively correcting such violations. This paper presents a novel approach to correcting accessibility violations on the web by modifying the document object model (DOM) in real time with foundation models. Leveraging accessibility error information, LLMs, and prompt engineering techniques, we achieved greater than a 51% reduction in accessibility violation errors after corrections on our novel benchmark: ACCESS. Our work demonstrates a valuable approach toward the direction of inclusive web content, and provides directions for future research to explore advanced methods to automate web accessibility.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (20)
  1. Artificial intelligence (ai) for web accessibility: Is conformance evaluation a way forward? W4A ’18. Association for Computing Machinery, 2018. URL https://doi.org/10.1145/3192714.3192834.
  2. Web accessibility challenges. International Journal of Advanced Computer Science and Applications, 7, 10 2016. URL http://dx.doi.org/10.14569/IJACSA.2016.071023.
  3. Dataset for evaluating the accessibility of the websites of selected latin american universities. Data in Brief, 28:105013, 2020. URL https://doi.org/10.1016/j.dib.2019.105013.
  4. Web accessibility: A digital divide for disabled people? In Eileen M. Trauth, Debra Howcroft, Tom Butler, Brian Fitzgerald, and Janice I. DeGross (eds.), Social Inclusion: Societal and Organizational Implications for Information Systems, pp.  217–228. Springer US, 2006. URL https://doi.org/10.1007/0-387-34588-4_15.
  5. Web accessibility challenges and perspectives: A systematic literature review. In 2016 11th Iberian Conference on Information Systems and Technologies (CISTI), pp.  1–6, 2016. URL https://doi.org/10.1109/cisti.2016.7521619.
  6. Jenny Craven. Web accessibility: a review of research and initiatives. 2006. URL https://api.semanticscholar.org/CorpusID:107165316.
  7. Dom-lm: Learning generalizable representations for html documents, 2022. URL https://arxiv.org/abs/2201.10608.
  8. Can a web accessibility checker be enhanced by the use of ai? In Klaus Miesenberger, Roberto Manduchi, Mario Covarrubias Rodriguez, and Petr Peňáz (eds.), Computers Helping People with Special Needs, pp.  67–73. Springer International Publishing, 2020. URL https://doi.org/10.1007/978-3-030-58796-3_9.
  9. Nicola Illingworth. The internet matters: Exploring the use of the internet as a research tool. Sociological Research Online, 6(2):79–90, 2001. URL https://doi.org/10.5153/sro.600.
  10. Towards the creation of accessibility agents for non-visual navigation of the web. SIGCAPH Comput. Phys. Handicap., (73–74):134–141, 2002. URL https://doi.org/10.1145/960201.957229.
  11. S. Kurt. Moving toward a universally accessible web: Web accessibility and education. Assistive Technology, vol. 31, no. 4, pp.  199–208, 2018. URL https://doi.org/10.1080/10400435.2017.1414086.
  12. Policy and Standards on Web Accessibility for Cognitive and Learning Disabilities, pp.  281–299. Springer London, 2019. URL https://doi.org/10.1007/978-1-4471-7440-0_16.
  13. Impact of web accessibility barriers on users with hearing impairment. DYNA, 82:233–240, 2015. URL https://doi.org/10.15446/dyna.v82n193.53499.
  14. Web accessibility - automatic/manual evaluation and authoring tools. In Klaus Miesenberger, Joachim Klaus, Wolfgang Zagler, and Arthur Karshmer (eds.), Computers Helping People with Special Needs, pp. 334–337. Springer Berlin Heidelberg, 2008. URL https://doi.org/10.1007/978-3-540-70540-6_49.
  15. Accessibility of healthcare sites: Evaluation by automated tools. Proceedings of International Conference on Data Science and Applications, pp.  625–636, 2021. URL https://doi.org/10.1007/978-981-16-5348-3_50.
  16. Web accessibility challenges for disabled and generation of alt text for images in websites using artificial intelligence. In 2022 3rd International Conference on Issues and Challenges in Intelligent Computing Techniques (ICICT), pp.  1–5, 2022. URL https://doi.org/10.1109/icict55121.2022.10064545.
  17. webaim. Webaim: The webaim million - an annual accessibility analysis of the top 1,000,000 home pages. Technical report, webaim.org, 2023. URL https://webaim.org/projects/million/.
  18. Measuring the accessability based on web content accessibility guidelines. In 2016 Joint Conference of the International Workshop on Software Measurement and the International Conference on Software Process and Product Measurement (IWSM-MENSURA), pp.  164–169, 2016. URL https://ieeexplore.ieee.org/document/7809604.
  19. Automatic alt-text: Computer-generated image descriptions for blind users on a social network service. In Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing, CSCW ’17, pp.  1180–1192. Association for Computing Machinery, 2017. URL https://doi.org/10.1145/2998181.2998364.
  20. React: Synergizing reasoning and acting in language models, 2023. URL https://arxiv.org/abs/2210.03629.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (8)
  1. Calista Huang (1 paper)
  2. Alyssa Ma (2 papers)
  3. Suchir Vyasamudri (1 paper)
  4. Eugenie Puype (1 paper)
  5. Sayem Kamal (1 paper)
  6. Juan Belza Garcia (1 paper)
  7. Salar Cheema (2 papers)
  8. Michael Lutz (4 papers)
Citations (1)
View on Semantic Scholar