AI-Based Personalised Learning Systems for Students with Special Educational Needs: A Machine Learning Approach

Abstract

AI-based personalised learning systems offer new opportunities to support students with Special Educational Needs by adapting content, pace, feedback, accessibility features, and learning pathways according to individual learner requirements. The present research examined teachers’ readiness to adopt AI-based personalised learning systems in SEN education using a quantitative survey and machine-learning approach. Data were collected from 150 teachers, special educators, SEN coordinators, counsellors, and educational technology professionals. The questionnaire measured AI awareness, perceived usefulness, digital competence, perceived accessibility benefits, ethical concerns, institutional support, and teacher readiness. Descriptive statistics, reliability analysis, correlation analysis, and machine-learning classification models were applied. The findings showed a high overall level of teacher readiness, with perceived usefulness, accessibility benefits, and digital competence showing the strongest positive relationships with readiness. Ethical concerns showed a negative relationship, indicating the importance of privacy, transparency, and responsible AI use. Among the machine-learning models, Random Forest achieved the best predictive performance, with perceived usefulness and accessibility benefits emerging as the strongest predictors. The findings suggest that AI-based personalised learning can support inclusive SEN education when implemented with teacher training, institutional support, accessibility-focused design, and ethical safeguards..