The week's pick
Random Articles
Reseach Article
An AI-Powered Early Detection System for Digital Burnout in Remote Workers using Behavioral and Interactional Data
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 187 - Number 93 |
| Year of Publication: 2026 |
| Authors: Benson-Emenike Mercy E., Onwuasoanya Ugochukwu K., Achi Ikenna K., Onwuachu Adaobi, Onungwe Helen Okparaji, Ubalatu Somkelechi Emmanuel |
10.5120/ijca2026926606
|
Benson-Emenike Mercy E., Onwuasoanya Ugochukwu K., Achi Ikenna K., Onwuachu Adaobi, Onungwe Helen Okparaji, Ubalatu Somkelechi Emmanuel . An AI-Powered Early Detection System for Digital Burnout in Remote Workers using Behavioral and Interactional Data. International Journal of Computer Applications. 187, 93 ( Mar 2026), 21-30. DOI=10.5120/ijca2026926606
Abstract
The growing trend of remote work has brought digital burnout on board as a significant occupational health issue, marked by psychological exhaustion and emotional strain from extended use of digital devices. This study conceived and created an AI-based early warning system that examines behavioral and interaction data to detect threats of digital burnout among remote workers and suggest early interventions. The solution employed the Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology, integrating a behavioral tracking module with system tracking APIs, an emotion inference engine through BERT-based sentiment analysis, a Random Forest machine learning model for burnout scoring, and a personalized recommendation system providing interventions. The solution was developed using Python libraries Scikit-learn, Transformers, and Streamlit, and testing was carried out using a synthetic dataset of 1,000 remote workers. The outcomes exhibited good performance with 79.5% accuracy, 0.76 precision on at-risk cases, 0.62 recall, and an ROC-AUC value of 0.88, reflecting good discrimination between at-risk and not-at-risk populations. The Streamlit web application deployed successfully combined all modules, offering a user-friendly interface for behavioral input data and sentiment analysis while presenting actionable wellness reports with tailored suggestions. This research contributes a proactive solution for organizational wellbeing management in remote work environments, bridges the gap between behavioral monitoring and sentiment analysis for comprehensive burnout assessment, and establishes a foundation for ethical AI application in workplace wellness monitoring that balances employee privacy with effective health intervention.
References
- Alabi, M. (2023). Transforming IT Work Environments: AI-Driven Solutions for Managing Employee Fatigue and Mental Health.
- AlOqaily, A. N., Qawasmeh, E. F., & Tawalbeh, J. (2025). The Effect of Implementing AI on Job Burnout Through the Mediating Role of Work-Life Balance in the Context of HRM. ECONOMICS-INNOVATIVE AND ECONOMICS RESEARCH JOURNAL, 13(2), 465-484.
- Benson-Emenike M. E. & Nwachukwu E.O. (2015) An Improved Intelligent Multi Biometric Authentication System. Communications on Applied Electronics (CAE) – ISSN : 2394-4714 Foundation of Computer Science FCS, New York, USA Volume 3– No.4, November 2015 – www.caeaccess.org
- Benson-Emenike M. E. and Ifeanyi-Reuben N. J. (2018) Network Learning And Training Of A Cascaded Link-Based Feed Forward Neural Network (CLBFFNN) In An Intelligent Trimodal Biometric System., International Journal of Artificial Intelligence and Applications (IJAIA) Vol.9, No.6, November 2018. DOI : 10.5121/ijaia.2018.9603 Page27
- Bhashitha Wendakoon Mudiyanselage, K. (2024). An intelligent web-based system with an analytical dashboard to monitor employee mental workload for better decision-making (Master's thesis, K. Bhashitha Wendakoon Mudiyanselage).
- Chawla, N., Gabriel, A. S., & O’Leary, K. (2025). AI-powered work-life blurring technologies: Implications for employee well-being and organizational performance. Journal of Applied Psychology, 110(3), 412-428.
- Emmerik, Ij.H. & Riet, Pim. (2025). How job demands, resources, and burnout predict objective performance: A constructive replication. Anxiety, stress, and coping. 21. 309-24. 10.1080/10615800801958637.
- FasterCapital (2025). Machine learning algorithms: Enhancing Behavioral Analytics with AI (Image). Retreived from https://fastercapital.com/content/Machine-learning-algorithms--Enhancing-Behavioral-Analytics-with-AI.html on July 1, 2025.
- Gupta, Kriti & Singh, Swati & Bhaskar, Preeti. (2016). Citizen adoption of e-government: A literature review and conceptual framework. Electronic Government, an International Journal. 12. 160. 10.1504/EG.2016.076134.
- Gupta, P., Sharma, M., & Joshi, S. (2025). Digital Health: Navigating Digital Transformation and Digital Stress. In Sustainable Digitalization Strategies in Business and Healthcare (pp. 261-294). IGI Global Scientific Publishing.
- Gupta, S., Lee, M. K., & Dabbish, L. (2025). Digital burnout in remote work: Causes, consequences, and coping strategies. Computers in Human Behavior, 134, 107312.
- Issa, H., Jaber, J., & Lakkis, H. (2024). Navigating AI unpredictability: Exploring technostress in AI-powered healthcare systems. Technological Forecasting and Social Change, 202, 123311.
- Mantello, P., & Ho, M. (2024). Emotional AI in the workplace: A new frontier for employee well-being. AI & Society, 39(2), 567-582.
- Mantello, P., & Ho, M. T. (2024). Emotional AI and the future of wellbeing in the post-pandemic workplace. AI & society, 39(4), 1883-1889.
- Margaret, Kagwe & Ngigi, Simon & Mutisya, Sabina. (2018). Sources of Occupational Stress and Coping Strategies among Teachers in Borstal Institutions in Kenya. Edelweiss: Psychiatry Open Access. 10.33805/2638-8073.111.
- Matthews, G., Cumings, R., De Los Santos, E. P., Feng, I. Y., & Mouloua, S. A. (2025). A new era for stress research: supporting user performance and experience in the digital age. Ergonomics, 68(6), 913-946.
- Mittal, S., Goel, A., & Singh, R. (2025). Machine learning for employee well-being: A systematic review. IEEE Transactions on Affective Computing, 16(1), 45-60.
- Mittal, S., Wijethilak, H. P., & Chandel, A. (2025). Effectiveness of AI-Powered Wellness in Promoting Employee Wellbeing and Happiness. In Insights on Wellbeing and Happiness in the Workplace (pp. 87-108). IGI Global Scientific Publishing.
- Mohammad, A. J. (2024). Chrono-Behavioral Fingerprinting for Workforce Optimization. International Journal of AI, BigData, Computational and Management Studies, 5(3), 91-101.
- Naik, K., Ghosh, S., Soni, H., & Singh, S. AI-Driven Burnout Detection & Eco-Volunteering: A Sustainable Employee Well-Being Model.
- Pavlopoulos, A., Rachiotis, T., & Maglogiannis, I. (2024). An overview of tools and technologies for anxiety and depression management using AI. Applied Sciences, 14(19), 9068.
- Rosca, C. M., & Stancu, A. (2024). Fusing Machine Learning and AI to Create a Framework for Employee Well-Being in the Era of Industry 5.0. Applied Sciences (2076-3417), 14(23).
- Sanni, B. (2023). An Integrated Framework for Mitigating IT Industry Burnout: Leveraging AI-Driven Work Pattern Monitoring to Enhance Workforce Wellbeing.
- Singh, L. (2024). Revolutionizing Care: Developing an AI-Human Synergy Mental Health Application for Mental Health Worker's Well-Being (Doctoral dissertation, Capella University).
- Tariq, M. U. (2025). AI and Work-Life Balance: Transforming Employee Wellbeing in the Modern Workplace. In Strengthening Human Relations in Organizations With AI (pp. 85-110). IGI Global Scientific Publishing.
- Vallu, V. R., Samudrala, V. K., & Pulakhandam, W. (2025). AI-Driven Digital Twin Framework for Accurate Mental Health Stress Detection and Personalized Management. In Accelerating Product Development Cycles With Digital Twins and IoT Integration (pp. 377-408). IGI Global Scientific Publishing.
Index Terms
Keywords