Using Machine Learning to Model EEG-Derived Brain Activity During Emotion Regulation
Bibliographic record
Abstract
Emotion Regulation (ER) is the ability to manage emotional responses. ER is important for maintaining mental health and handling social interactions, especially under stress. This study explores the brain activity involved in ER using electroencephalography (EEG) and machine learning (ML) models to predict successful and unsuccessful ER. Study participants viewed emotional and neutral images under two conditions: regular viewing and being asked to reduce their emotions. At the end of each experimental trial, participants rated the intensity of their emotional response to the image. Ratings of low intensity (1 and 2) were classified as successful ER, whereas ratings of high intensity (3 and 4) were considered indicative of unsuccessful ER. EEG signals were analyzed in both time and frequency domains to identify patterns linked to ER. In the time domain, significant differences in Global Field Power (GFP) were observed, especially in the frontal and central regions of the brain. Frequencydomain analysis using Power Spectral Density (PSD) showed that theta, beta, and gamma bands were important for regulating emotions. Using these analysis results, machine learning models were trained to predict regulation success. Among the models, a neural network with Maximum Mean Discrepancy (MMD) loss performed the best, achieving an F1-score macro of 75.57% with a subject-independent approach. These machine-learning models highlight the importance of frontal and central brain regions and beta brain frequency signals in the prediction of ER levels. It shows that combining EEG data with advanced machine learning methods can create accurate models for understanding and predicting emotional responses. Additionally, this integrated EEG-based approach represents a novel framework for ER assessment, offering a promising direction for future research and enabling personalized mental health treatments.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".