Computational Approaches for Emotional Burnout Detection: Machine Learning and Deep Learning Evaluation
DOI:
https://doi.org/10.64915/RADAP.2026.103.%25pKeywords:
emotional burnout, machine learning, deep learning, electroencephalography, maslach burnout inventory, feature selection, classification, mental health diagnosticsAbstract
This study focuses on the development and evaluation of computational techniques for classifying emotional burnout based on quantitative data analysis. Instead of relying on subjective psychometric questionnaires, we investigate the applicability of machine learning and deep learning algorithms to structured datasets. Several classical methods, including logistic regression, random forest, and gradient boosting, were systematically compared with a Deep Learning (DL) ensemble model. To enhance robustness, preprocessing steps such as feature selection, data balancing, and resampling were applied. The deep learning architecture, incorporating focal loss and adaptive threshold optimization, achieved the best performance. On 5-fold cross-validation, the proposed DL model obtained an overall accuracy of 86.3%, with precision of 0.815/0.887, recall of 0.786/0.904, and F1-scores of 0.800/0.895 for the negative and positive classes respectively. The results demonstrate that advanced computational models can provide scalable and generalizable tools for automatic detection tasks, forming a technical foundation for future integration into applied research and occupational health monitoring systems.
References
1. Van Luijtelaar G. V., Verbraak M., van den Bunt M., Keijsers G., and Arns M. (2010). EEG findings in burnout patients. The Journal of Neuropsychiatry and Clinical Neurosciences, Vol. 22, No. 2, pp. 208-217. DOI: 10.1176/jnp.2010.22.2.208.
2. Golonka K., Gawlowska M., Mojsa-Kaja J., and Marek T. (2019). Psychophysiological characteristics of burnout syndrome: Resting-state EEG analysis. BioMed Research International, 2019, Article ID 3764354. DOI: 10.1155/2019/3764354.
3. Tement S., Pahor A., and Jaušovec N. (2016). EEG alpha frequency correlates of burnout and depression: The role of gender. Biological Psychology, Vol. 114, pp. 1-12. DOI: 10.1016/j.biopsycho.2015.11.005.
4. Guo Y., Park J., and Kang S. (2024). Effects of job crafting and leisure crafting on nurses’ burnout: A machine learning approach. International Journal of Environmental Research and Public Health, Vol. 21, No. 7, Article 1191915. DOI: 10.1155/2024/9428519.
5. Van Zyl-Cillié L., Le Roux D. B., and Engelbrecht A. (2024). Machine learning model to predict burnout risk factors among South African nurses. Healthcare, Vol. 12, No. 16, Article 1662. DOI: 10.1186/s12913-024-12184-5.
6. Badr Y. (2024). A review on evaluating mental stress by deep learning using EEG. Neural Computing and Applications, Vol. 36, No. 6, pp. 2849-2871. DOI: 10.1007/s00521-024-09809-5.
7. Kim H.-G., Jeong D.-K., and Kim J.-Y. (2022). Emotional stress recognition using EEG signals based on a three-dimensional convolutional gated self-attention deep neural network. Applied Sciences, Vol. 12, No. 21, Article 11162. DOI: 10.3390/app122111162.
8. Bianchi R., Schonfeld I. S., and Laurent E. (2017). Biological research on burnout-depression overlap: Long-standing limitations and on-going reflections. Neuroscience and Biobehavioral Reviews, Vol. 83, pp. 238-239. DOI: 10.1016/j.neubiorev.2017.10.019.
9. Afek N., Harmatiuk D., Gawlowska M., Ferreira J. M. A., Golonka K., Tukaiev S., Popov A., and Marek T. (2025). Functional connectivity in burnout syndrome: a resting-state EEG study. Frontiers in Human Neuroscience, Vol. 19, Article 1481760. DOI: 10.3389/fnhum.2025.1481760.
10. Kakkos, I., Tzavellas, E., Feleskoura, E., Mourtakos, S., Kontopodis, E., et al. (2025). EEG-Based Assessment of Cognitive Resilience via Interpretable Machine Learning Models. AI, 6(6), 112. DOI: 10.3390/ai6060112.
11. Hamid, N. H. A., Sulaiman, N., Aris, S. A. M., Murat, Z. H., Taib, M. N. (2010). Evaluation of human stress using EEG power spectrum. Proceedings of the 6th International Colloquium on Signal Processing & Its Applications (CSPA). DOI: 10.1109/CSPA.2010.5545282.
12. Khan, T., Javed, H., Amin, M., Usman, O., Hussain, S. I., Mehmoood, A., and Maple, C. (2021). EEG Based Aptitude Detection System for Stress Regulation in Health Care Workers. Scientific Programming, Article ID 4620487. DOI: 10.1155/2021/4620487.
13. Arif, A., Wang, Y., Yin, R., Zhang, X., Helmy, A. (2024). EF-Net: Mental State Recognition by Analyzing Multimodal EEG-fNIRS via CNN. Sensors, 24(6), 1889. DOI: 10.3390/s24061889.
14. Liu Z. and Zhao J. (2025). Leveraging deep learning for robust EEG analysis in mental health monitoring. Frontiers in Neuroinformatics, Vol. 18, Article 1494970. DOI: 10.3389/fninf.2024.1494970.
15. Al-Shargie F., Badr Y., Tariq U., Babiloni F., Al-Mughairbi F., and Al-Nashash H. (2023). Classification of mental stress levels using EEG connectivity and convolutional neural networks. Proceedings of the 45th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), DOI: 10.1109/EMBC40787.2023.10340398.
16. Wang, X., He, Y., Zhao, Y., Zhang, Y., and Li, Y. (2021). Multi-modal brain network analysis using graph convolutional networks for major depressive disorder classification. Medical Image Analysis, 72, 102123. DOI: 10.1016/j.media.2021.102123.
17. Yeo, W.-H., Kim, Y.-S., Lee, J., and Rogers, J. A. (2012). Multifunctional Skin-Like Electronics for Long-Term Health Monitoring. Proceedings of the ASME 2012 International Mechanical Engineering Congress and Exposition. DOI: 10.1115/IMECE2012-85698.
18. Mushta S. A., Palamar S. P., Harmatiuk D. V., Popov A. O., Alves Ferreira J. M., Makarchuk M. Yu., and Tukaiev S. V. (2025). EEG frequencies pattern as brain signature of emotional burnout: Anxiety-tension stage formation. Clinical and Preventive Medicine, No. 1, pp. 92-100. DOI: 10.31612/2616-4868.1.2025.12.
19. Chawla, N. V., Bowyer, K. W., Hall, L. O., and Kegelmeyer, W. P. (2002). SMOTE: Synthetic Minority Over-sampling Technique. Journal of Artificial Intelligence Research, 16, 321–357. DOI: 10.1613/jair.953.
20. Varoquaux, G. (2018). Cross-validation failure: Small sample sizes lead to large error bars. NeuroImage, 180, 68–77. DOI: 10.1016/j.neuroimage.2017.06.061.
21. Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., et al. (2011). Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 12, pp. 2825–2830.
22. Kingma D. P., Ba J. (2015). Adam: A Method for Stochastic Optimization. arXiv preprint arXiv:1412.6980.
23. Lin T.-Y., Goyal P., Girshick R., He K., and Dollár P. Focal Loss for Dense Object Detection, IEEE International Conference on Computer Vision (ICCV), 2017.
24. Zunair H. and Ben Hamza A. (2020). Melanoma Detection using Adversarial Training and Deep Transfer Learning. arXiv preprint arXiv:2004.06824.
25. Yeung M., Sala E., Schönlieb C.-B., and Rundo L. (2021). Unified Focal Loss: Generalising Dice and Cross Entropy-Based Losses to Handle Class Imbalanced Medical Image Segmentation. arXiv preprint arXiv:2102.04525.
26. Pandiyaraju V., Malarvannan S., Venkatraman S., Abeshek A., Priyadarshini B., and Kannan A. (2024). A Novel Adaptive Hybrid Focal-Entropy Loss for Enhancing Diabetic Retinopathy Detection Using Convolutional Neural Networks. arXiv preprint arXiv:2411.10843.
27. Ganaie M. A., Hu M., Malik A. K., Tanveer M., and Suganthan P. N. (2021). Ensemble deep learning: A review. arXiv preprint arXiv:2104.02395, pp. 1–35.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 С. А. Мушта, І. А. Мушта , А. О. Попов, О. М. Лисенко, С. В. Тукаєв
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
