Dataset for Towards a Conceptual Model for AI-Driven Web Accessibility Remediation: A Prompt-Based Approach

This dataset supports the transparency and reproducibility of the scoping review and procedures reported in the article "Towards a Conceptual Model for AI-Driven Web Accessibility Remediation: A Prompt-Based Approach."

The folder "01-Related Work search results" documents the initial automated search process conducted in the Scopus and Web of Science databases. It includes the retrieved records based on the filters applied during the preliminary review of related literature.

The folder "02-Automatic search results" contains the subsequent search stages carried out across selected digital library databases (Scopus, Web of Science, and arXiv). It includes exported bibliographic records organized by search strings, as well as the inclusion and exclusion steps applied.

The file "Dataset_Towards_accessible_website_through_AI.xlsx" serves as the main dataset. It contains fully curated data from the entire review process, including metadata for the selected studies: titles, venues, publication year, AI techniques, LLMs used, prompting strategies, evaluation methods, and referenced accessibility standards. It also includes raw and normalized quality assessment scores, aligned with the PRISMA-ScR methodology adapted for software engineering research.

Together, these materials enable full reproducibility of the review and provide a structured foundation for future research in AI-assisted web accessibility.

本数据集为论文《面向人工智能驱动的网页可访问性修复的概念模型：一种基于提示词的方法》中所报告的范围综述及其研究流程的透明度与可复现性提供支撑。

文件夹"01-Related Work search results"记录了在Scopus与Web of Science数据库中开展的初始自动化检索流程，涵盖初步文献综述阶段基于预设筛选条件获取的检索记录。

文件夹"02-Automatic search results"包含后续在选定数字图书馆数据库（Scopus、Web of Science及arXiv）中开展的多阶段检索内容，收录了按检索式整理导出的文献题录记录，以及对应的文献纳入与排除流程步骤。

文件"Dataset_Towards_accessible_website_through_AI.xlsx"为本数据集的核心文件，收纳了整个综述流程中经全面甄选整理的完整数据，包括入选研究的元数据：研究标题、发表载体、出版年份、人工智能技术、所使用的大语言模型（Large Language Model，LLM）、提示策略、评估方法，以及所引用的网页可访问性标准。此外还包含原始与标准化的质量评估得分，适配软件工程研究场景的PRISMA-ScR方法体系。

上述所有材料共同保障了该综述的完整可复现性，并为人工智能辅助网页可访问性领域的后续研究提供了结构化的研究基础。