Preference vs. Performance: EEG-Based Classification of Learner Engagement in Multimodal Instruction

2026-10-04

AI Summary

This study addresses the limitations of static user profiles in adaptive learning systems and the ongoing debate surrounding the matching hypothesis by investigating the relationship between instructional preferences and neurophysiological engagement. Integrating multimodal learning analytics (MMLA) with electroencephalography (EEG), brain signals were acquired using Emotiv EPOC X and OpenBCI devices. Through spectral analysis and binary logistic regression modeling, the research quantified how learning preferences modulate neural markers of attention and cognitive processing across multimodal contexts. Results indicate that while revealing preferences did not directly enhance academic performance, it significantly modulated theta and alpha band activity, with OpenBCI achieving a classification accuracy of 83.21%. This work validates the feasibility of quantifying learning engagement via neural signals, providing a non-invasive input foundation for adaptive algorithms.

Abstract

Effective adaptive instructional systems require robust measures of learner engagement that go beyond static user profiles. This study employs Multimodal Learning Analytics (MMLA) to investigate the relationship between self-reported instructional modality preferences and objective neurophysiological markers of engagement. Thirty-seven participants engaged with learning content delivered via varying modalities (visual, auditory, reading/writing, kinesthetic). We captured real-time neural activity using two EEG devices: the Emotiv EpocX (14 channels, 128 Hz) and OpenBCI (16 channels, 125 Hz). Preferences were assessed using the VARK questionnaire. Consistent with literature challenging the"meshing hypothesis,"aligning instructional modality with stated preferences did not significantly predict performance gains. However, spectral analysis of EEG data revealed divergent engagement patterns: when content aligned with preferences, distinct neural activity patterns emerged in theta and alpha frequency bands-markers associated with attention and cognitive processing. These signals were used to train a binary logistic regression classifier, achieving a mean accuracy of 83.21% with OpenBCI and 56.27% with Emotiv EpocX. These findings suggest that while self-reported preferences may not dictate learning outcomes, they significantly influence neurophysiological engagement, offering a viable, non-invasive input for adaptive educational algorithms.

Problem

• learner engagement
• multimodal instruction
• EEG
• modality preference
• adaptive instructional systems

Innovation

• Multimodal Learning Analytics
• EEG-based Classification
• Learner Engagement
• Spectral Analysis
• Adaptive Instructional Systems