Prediction of Attention-Deficit and Hyperactivity Disorder in Online Learning

Abstract

The rise of online learning poses challenges in identifying and supporting students with cognitive disorders, notably ADHD. This neurodevelopmental disorder, diagnosed in childhood, impacts academic performance. With the prevalence of online education, early detection and intervention for ADHD are crucial. Predictive techniques using digital traces, behavioral patterns, and physiological data during online sessions are studied. Machine and deep learning models, including supervised and unsupervised approaches, identify ADHD-related behaviors. Natural language processing analyzes textual interactions for signs of inattention or hyperactivity. Eye-tracking and physiological sensors reveal attention levels during online activities. Though offline classrooms allow direct interaction, these techniques enable timely interventions, enhancing ADHD students' experiences in the digital learning era. Further research to refine and address challenges will contribute to a more inclusive and effective online learning environment.