A Study on the Use of LLM Prompts for Evaluating Web Accessibility of City Hall Portals in the Sertões dos Crateús Region

  • Lúcio Cauper Freitas de França UFC
  • Lisieux Marie M. dos S. Andrade UFC
  • Windson Viana de Carvalho UFC

Abstract


This study is an initial investigation into the use of Large Language Models (LLMs) with prompts written in Portuguese for web accessibility evaluation, using a set of 13 municipal government portals as a case study. ChatGPT 4o was employed to verify 37 success criteria from WCAG 2.2, and its coverage was compared with that of the automated inspection tools IBM, Achecker, andWAVE. Preliminary results indicate that the LLM provides positive contributions as a support tool in the web accessibility verification process.

Keywords: Large Language Models, accessibility, web

References

Associação Brasileira de Normas Técnicas ABNT. 2025. ABNT NBR 17225:2025 — Acessibilidade em conteúdo e aplicações web - Requisitos. [link]

Danyllo Albuquerque, Gustavo Ponciano, João Pedro, Arlan Santos, Fabrício Silva, Caíque Oliveira, Felipe Vasconcelos, and Thiago Honorato. 2024. Análise da Conformidade com Acessibilidade Digital: Um Estudo no Contexto dos Websites das Universidades Federais Brasileiras. In Workshop de Computação Aplicada em Governo Eletrônico (WCGE). SBC, 133–144.

Yang Bai. 2019. The relationship between website accessibility and usability: an examination of us county government online portals. Electronic Journal of e-Government 17, 1 (2019), pp47–62.

Brasil. 2011. Lei n° 12.527, de 18 de novembro de 2011. Diário Oficial da União. [link]

Brasil. 2015. Lei n° 13.146, de 6 de julho de 2015. Diário Oficial da União. [link]

Governo Federal Brasil. 2023. Modelo de Acessibilidade de Governo Eletrônico (eMAG) – Versão 3.1.

Julielen A Dorneles and Amanda M Melo. 2024. Avaliação Preliminar da Acessibilidade de Sites de Prefeituras dos Municípios em que estão situados os Campi da Unipampa. In Escola Regional de Engenharia de Software (ERES). SBC, 70–78.

Ziyao He, Syed Fatiul Huq, and Sam Malek. 2025. Enhancing Web Accessibility: Automated Detection of Issues with Generative AI. Proceedings of the ACM on Software Engineering 2, FSE (2025), 2264–2287.

Wenjun Lin, Bamikole Adewale, Min Li, Mahreen Nasir, Ajmery Sultana, Rashid Hussain Khokhar, and Yue Zhang. 2025. Dynamic Web Page Modification for Accessibility Using AI and Large Language Models. In Computer and Information Science and Engineering: Volume 18. Springer, 33–46.

Juan-Miguel López-Gil and Juanan Pereira. 2025. Turning manual web accessibility success criteria into automatic: an LLM-based approach. Universal Access in the Information Society 24, 1 (2025), 837–852.

João Marcelo Alves Macedo, Valdecir Becker, Felipe Melo Feliciano de Sá, Edvaldo Vasconcelos da Rocha Filho, and Daniel de Queiroz Cavalcanti. 2025. Avaliação de sistemas de Governo Aberto e de transparência pública nas capitais brasileiras. Cadernos Gestão Pública e Cidadania 30 (2025), e90832.

Rafael Pardini, João Bárbara, Henrique Scheid, Adriano CM Pereira, Wagner Meira Jr, Reinaldo Ferraz, and Beatriz Rocha. 2021. Observatório da acessibilidade da web brasileira. In Simpósio Brasileiro de Sistemas Multimídia eWeb (WebMedia). SBC, 71–74.

Cleber Cristiano Prodanov and Ernani Cesar De Freitas. 2013. Metodologia do trabalho científico: métodos e técnicas da pesquisa e do trabalho acadêmico-2ª Edição. Editora Feevale.

G Pradeep Reddy, YV Pavan Kumar, and K Purna Prakash. 2024. Hallucinations in large language models (LLMs). In 2024 IEEE Open Conference of Electrical, Electronic and Information Sciences (eStream). IEEE, 1–6.

Ather Sharif, Sanjana Shivani Chintalapati, Jacob O Wobbrock, and Katharina Reinecke. 2021. Understanding screen-reader users’ experiences with online data visualizations. In Proceedings of the 23rd International ACM SIGACCESS Conference on Computers and Accessibility. 1–16.

Sudesh Sheoran, S Mohanasundaram, R Kasilingam, and Sanket Vij. 2023. Usability and accessibility of open government data portals of countries worldwide: an application of TOPSIS and entropy weight method. International Journal of Electronic Government Research (IJEGR) 19, 1 (2023), 1–25.

World Wide Web Consortium W3C. 2023. Web Content Accessibility Guidelines (WCAG) 2.2.

Chaozheng Wang, Zongjie Li, Cuiyun Gao, Wenxuan Wang, Ting Peng, Hailiang Huang, Yuetang Deng, Shuai Wang, and Michael R Lyu. 2024. Exploring multi-lingual bias of large code models in code generation. arXiv preprint arXiv:2404.19368 (2024).
Published
2025-11-10
FRANÇA, Lúcio Cauper Freitas de; ANDRADE, Lisieux Marie M. dos S.; CARVALHO, Windson Viana de. A Study on the Use of LLM Prompts for Evaluating Web Accessibility of City Hall Portals in the Sertões dos Crateús Region. In: BRAZILIAN SYMPOSIUM ON MULTIMEDIA AND THE WEB (WEBMEDIA), 31. , 2025, Rio de Janeiro/RJ. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2025 . p. 580-584. DOI: https://doi.org/10.5753/webmedia.2025.16064.

Most read articles by the same author(s)