Prediction of web page accessibility based on structural and textual features

  • Authors:
  • Sina Bahram;Debadeep Sen;Robert St. Amant

  • Affiliations:
  • North Carolina State University, Raleigh, NC;North Carolina State University, Raleigh, NC;North Carolina State University, Raleigh, NC

  • Venue:
  • Proceedings of the International Cross-Disciplinary Conference on Web Accessibility
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper we present an approach to assessing the accessibility of Web pages, based on machine learning techniques. We are interested in the question of whether there are structural and textual features of Web pages, independent of explicit accessibility concerns, that nevertheless influence their usability for people with vision impairment. We describe three datasets, each containing a set of features corresponding to Web pages that are "Accessible" or "Inaccessible". Three classifiers are used to predict the category of these Web pages. Preliminary results are promising; they suggest the possibility of automated classification of Web pages with respect to accessibility.