Webpage Accessibility Evaluation Using Machine Learning Technique

Abstract

In this digital era, web becoming a crucial and prime source of information for various areas. Having a wide array of advantages, sometimes web can create several difficulties for people with disabilities while navigating the information. Thus, it is important to ensure website navigation without any difficulties. On this focus, the aim of this study is to evaluate website accessibility through Decision Tree (DT), a machine learning technique to ensure the benefits of this platform among a wide array of people. The implemented machine learning technique incorporated Mauve-generated data to calculate the overall accessibility barrier in terms of several accessibility guidelines and checkpoints from the Web Content Accessibility Guideline (WCAG 2.1) criteria. The performance of the ML method was validated through confusion matrix and classification report results. It is worth mentioning that none of the selected webpages were found free from accessibility errors. Also, the experimental results depict that it is urgent to focus on web accessibility policies to strengthen this domain for better directives in this area to improve social inclusiveness.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 6 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.