Advances in Brain-Computer Interfaces and Neural Integration
Neurofeedback and Code Comprehension: Brain-Computer Interfaces in the Evaluation of Student Learning in Programming Courses
Abstract
Ismail Olaniyi Muraina, Moses Adeolu Agoi, Abam Solomon Onen, Wasiu Olatunde Oladapo and Bashir Oyeniran Ayinde
This study examines the potential of brain-computer interface (BCI) technology, specifically EEG-based neurofeedback, in evaluating student learning during programming courses. A simulated quantitative design was employed, using simulated EEG-like metrics (attention, cognitive load, and fatigue) for 60 undergraduate computer science students, alongside academic performance indicators such as comprehension scores, error rates, and task completion times. Pearson correlation analysis revealed strong positive relationships between attention and comprehension (r = 0.70, p < 0.01) and significant negative correlations between cognitive load/fatigue and student performance. Multiple regression analysis revealed that attention significantly predicted comprehension scores (β = +0.305, p < 0.001), whereas cognitive load and fatigue hurt learning outcomes. Cluster analysis identified distinct cognitive profiles that aligned with student performance. These findings suggest that BCI-derived neurofeedback can offer real-time insights into student engagement and learning efficacy, positioning neurotechnology as a promising complement to traditional assessment in computing education.