E-Learning Accessibility: Barriers and solutions for inclusive online education

Abstract

The rapid growth of e-learning has highlighted serious accessibility problems, particularly for students with different needs. This research looks at the barriers to e-learning accessibility and offers solutions in order to create inclusive online education systems. The technique consists of textual data processing for preprocessing, domain knowledge integration for feature selection, and the K-Nearest Neighbours (KNN) algorithm for classification. Preprocessing involves evaluating textual data from user feedback, forum discussions, and course engagements to identify significant accessibility issues. Domain knowledge guides feature selection, ensuring that crucial elements like device compatibility, internet bandwidth, and assistive tool use are taken into account. The KNN model classifies students based on their accessibility needs and predicts the likelihood that they will successfully complete the course. The results demonstrate that by effectively detecting accessibility hurdles and offering tailored solutions, this approach enhances student outcomes. This research promotes the development of flexible e-learning platforms by emphasising the significance of universal access to high-quality education.