Citation :

Pooja Sithrubi Gnanasambanthan, K.S Gayathri, M. Gnana Priya , 2025. "Rule-Based AI-Assisted Burnout Assessment and Personalized Music Recommendation System" ESP International Journal of Advancements in Science & Technology (ESP-IJAST)  Volume 3, Issue 4: 28-37.

Abstract :

Burnout has become a major opportunity in occupational health among the information technology (IT) professionals working in multinational companies (MNCs) influenced by asymmetric work time, long working hours, high cognitive load and constant digital continuity. These factors lead to chronic stress, sleep deprivation, a decline in productivity, and/or various mental health problems [1], [2]. Traditional burnout evaluation methods primarily reactive, relying on self-reported assessments coupled with post-hoc interventions which reduces the effectiveness of preventive mental health care. To fill this gap, a rule-based artificial intelligence (AI) system for assisting burnout assessment and personalized music recommendation is proposed in this paper to contribute as an explainable and lightweight alternative for burnout monitoring and intervention. Simply put, the system assesses burnout levels by using structured stress scores and emotion indicators through deterministic decision rules that are based on expert domain knowledge and established emotional frameworks [8], [11]. From the analyzed burnout category, personalized music playlists are generated in alignment with prior evidence that suggests music can influence stress responses [9], [10] to mitigate and regulate emotions. The proposed framework extends earlier work on multimodal emotion recognition and recommendation system [16] toward burnout-aware intervention. The experimental evaluation shows good agreement between system-generated classifications of burnout labels and expert-annotated ones, with 88.6% of the pairs possible to match with an acceptable rate for each group which makes them align with human assessment. These findings indicate that rule-based AI systems provide transparent, dependable solutions for burnout assessment and supportive mental well-being interventions that are suitable for practical implementation [32–34].

References :

[1] C. Maslach and M. P. Leiter, “Understanding the burnout experience: Recent research and its implications for psychiatry,” World Psychiatry, vol. 15, no. 2, pp. 103–111, Jun. 2016.

[2] A. S. G. Schaufeli, W. B. Schaufeli, and T. Taris, “Burnout: Conceptual and measurement issues,” Work & Stress, vol. 19, no. 3, pp. 256–262, 2005.

[3] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016.

[4] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” in Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), 2012, pp. 1097–1105.

[5] G. B. Huang, M. Ramesh, T. Berg, and E. Learned-Miller, “Labeled faces in the wild: A database for studying face recognition in unconstrained environments,” Tech. Rep., Univ. Massachusetts, Amherst, 2007.

[6] S. Li and W. Deng, “Deep facial expression recognition: A survey,” IEEE Trans. Affective Computing, vol. 13, no. 3, pp. 1195–1215, Jul.–Sep. 2022.

[7] F. Eyben, K. R. Scherer, B. W. Schuller, et al., “The Geneva minimalistic acoustic parameter set (GeMAPS) for voice research and affective computing,” IEEE Trans. Affective Computing, vol. 7, no. 2, pp. 190–202, Apr.–Jun. 2016.

[8] R. Picard, Affective Computing. Cambridge, MA, USA: MIT Press, 1997.

[9] M. S. Thoma, R. La Marca, R. Brönnimann, L. Finkel, U. Ehlert, and U. Nater, “The effect of music on the human stress response,” PLoS One, vol. 8, no. 8, pp. 1–10, Aug. 2013.

[10] J. H. Lee, “The effects of music on stress and mood in daily life,” Psychology of Music, vol. 44, no. 3, pp. 512–526, 2016.

[11] D. B. Goleman, “Emotional intelligence: Why it can matter more than IQ,” Bantam Books, New York, USA, 1995.

[12] T. Baltrusaitis, A. Zadeh, Y. C. Lim, and L.-P. Morency, “OpenFace 2.0: Facial behavior analysis toolkit,” in Proc. IEEE Int. Conf. Automatic Face & Gesture Recognition, 2018, pp. 59–66.

[13] M. Abadi et al., “TensorFlow: A system for large-scale machine learning,” in Proc. 12th USENIX Symp. Operating Systems Design and Implementation (OSDI), 2016, pp. 265–283.

[14] Activity Watch Developers, “Activity Watch: Open-source time tracking and analytics,” 2023. [Online]. Available: https://activitywatch.net

[15] M. Reisslein, “Web-based real-time monitoring systems for human-centered applications,” IEEE Access, vol. 8, pp. 145612–145624, 2020.

[16] Pooja Sithrubi Gnanasambanthan “AI-Driven Multimodal Emotion Recognition and Recommendation via Power BI”, IJERESM, Vol. 4, Issue 3, pp.42-51, Jul-Sep 2025

Keywords :

Burnout Assessment, Rule-Based Artificial Intelligence, Emotion-Aware Systems, Stress Monitoring, Personalized Music Recommendation, Mental Well-Being.