EEG Transformer for Classifying Students’ Epistemic Cognition States in Educational Contexts
Epistemic cognition encompasses the processes by which individuals achieve knowledge and understanding and is pivotal in human learning, typically in educational settings. Despite its importance, epistemic cognition is often studied using traditional educational research methods such as questionnair...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10870110/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Epistemic cognition encompasses the processes by which individuals achieve knowledge and understanding and is pivotal in human learning, typically in educational settings. Despite its importance, epistemic cognition is often studied using traditional educational research methods such as questionnaires and interviews. However, these methods primarily rely on self-reporting and retrospective accounts, which may not effectively capture the dynamic, situational, and often implicit nature of epistemic cognition as it unfolds in real-time learning environments. This study addresses this limitation by employing transformers and publicly available electroencephalography (EEG) datasets to classify students’ epistemic cognition states. For the first time, we demonstrate that transformers, enhanced with educational domain-specific preprocessing and categorical embeddings, achieve state-of-the-art performance in classifying epistemic cognition across diverse contexts. Our model achieved an accuracy of 99.63% and 99.65% for distance learning and online understanding tasks, respectively, outperforming existing transformers in cognition and metacognition studies. Grounded in the Learning Sciences, which emphasize an interdisciplinary and scientific approach to understanding human learning, this applied research demonstrates the transformative potential of integrating artificial intelligence with education and neuroscience to generate actionable insights into educational practices. |
|---|---|
| ISSN: | 2169-3536 |