Adaptive Learning Tool to Enhance Educational Outcomes for Students with Inattentive Attention Deficit Hyperactivity Disorder (ADHD)

This paper presents an adaptive learning tool to enhance educational outcomes for students with inattentive ADHD. The platform comprises four key components: content chunking and simplification with interactive content, an adaptive quizzing system, a personalized ADHD identifier and break recommendation system, and a tool to maximize learning potential. The content chunking component transforms traditional educational materials into ADHD-friendly formats using Natural Language Processing (NLP) technologies, making them more accessible and engaging. The adaptive quizzing system employs a modified spaced repetition algorithm to optimize memory retention and engagement through personalized quizzes. The personalized ADHD identifier uses a hybrid Convolutional Neural Network (CNN) model to analyze webcam data, tracking head movements and facial emotions to provide real-time break recommendations, enhancing focus and cognitive performance. The final component integrates machine learning and data mining to adaptively assign tasks and provide personalized feedback, fostering a supportive learning environment. Preliminary evaluations indicate significant improvements in academic performance and engagement among ADHD-diagnosed students. This research underscores the potential of adaptive learning technologies in creating inclusive educational environments addressing the unique challenges faced by students with ADHD.