This paper presents a methodological approach to user modeling focused on learning styles. While EEG has been widely used for real-time detection of attention and workload, few studies have integrated brain signals with validated learning style instruments for long-term modeling. Addressing this gap, we recorded EEG data from 15 participants performing three cognitive tasks—visual, auditory, and practice-based—and evaluated their learning styles using the VARK questionnaire. A custom dashboard was developed for signal processing, frequency band analysis, and visualization. From the processed EEG data, dominant neural patterns were extracted, and clustering algorithms were used to group users by their brainwave features. Results showed 80% alignment between EEG-derived dominant bands and reported learning preferences, further validated by user experience scores (UEQ). These findings suggest that low-cost EEG devices can effectively support implicit user modeling in adaptive educational systems.
Ortega-Zenteno et al. (Mon,) studied this question.