Computation of Accessibility Score of Educational Institute Webpages using Machine Learning Approaches

Sikné Lányi, Cecília and Ara, Jinat (2024) Computation of Accessibility Score of Educational Institute Webpages using Machine Learning Approaches. INFOCOMMUNICATIONS JOURNAL, 16 (Specia). pp. 49-57. ISSN 2061-2079

Preview

Text InfocomJournal_2024_SpecISS_CogInf_CogAspVR_6.pdf - Published Version Download (2MB) | Preview

Abstract

The availability of digital platforms by ensur ing accessibility and usability is considered a virtual gateway to provide a wide array of information to its stakeholders. An accessible web platform can disseminate information among a variety of target audiences. Thereby accessibility of academic web pages requires special attention. Herein we proposed an accessibility computation approach for higher education in stitute webpage (Homepage) in the context of universities in Hungary. The proposed approach incorporated two machine learning (ML) classifiers: Random Forest (RF), and Decision Tree (DT) to experiment on our custom dataset to compute the overall accessibility score. Performance of ML methods vali dated through confusion matrix and classification report result. The empirical results of ML methods and statistical evaluation showed poor accessibility scores which depicts that none of the selected web pages are free from accessibility issues associ ated with disabilities. As such, accessibility is a crucial aspect that needs further concern as most of the considered academic webpages have experienced accessibility issues and showed im provement demands. Abstract—The availability of digital platforms by ensuring accessibility and usability is considered a virtual gateway to provide a wide array of information to its stakeholders. An accessible web platform can disseminate information among a variety of target audiences. Thereby accessibility of academic web pages requires special attention. Herein we proposed an accessibility computation approach for higher education institute webpage (Homepage) in the context of universities in Hungary. The proposed approach incorporated two machine learning (ML) classifiers: Random Forest (RF), and Decision Tree (DT) to experiment on our custom dataset to compute the overall accessibility score. Performance of ML methods validated through confusion matrix and classification report result. The empirical results of ML methods and statistical evaluation showed poor accessibility scores which depicts that none of the selected web pages are free from accessibility issues associated with disabilities. As such, accessibility is a crucial aspect that needs further concern as most of the considered academic webpages have experienced accessibility issues and showed im provement demands.

Actions (login required)

Edit Item