Year: 2026
Type: dissertation
Study design: Observational Study
Abstract: This thesis investigates the prevalence and predictors that contribute to elevated burnout scores.Hence it contributes to Good Health and Well-being -third goal of the United Nations Sustainable Development Goals.By applying Copenhagen Burnout Inventory and adapting Job Demands-Resources model, the thesis shows that the burnout in the Information Technology sector can be explained through organizational, psychological and technological demands and resources.By integrating qualitative interview findings, regression and predictive analysis, the thesis brings a comprehensive framework for understanding the presence of burnout in IT as well as the key drivers that contribute to its elevation.This way companies can use those for making the work environments healthier and productive which aligns with the eighth Sustainable Development Goal (Decent Work and Economic Growth).Machine Learning models, including Linear Regression, Extreme Gradient Boosting, Random Forest, Support Vector Regression and Neural Networks were developed to predict burnout levels, which aligns with ninth goal of Sustainable Development Goals (Industry, Innovation and Infrastructure).Even though the used models didn't perform so well, the thesis suggests that Linear Regression provides considerable accuracy, therefore, it can be utilized for predicting burnout in IT employees and achieving acceptable results.
Author: Isajloska, Keti
Institution: University of Ljubljana
Language: English
Topic: Stress and Burnout Research
Subfield: Social Psychology
Field: Psychology
Domain: Social Sciences
Keywords: burnout, IT professionals, burnout prediction, Copenhagen Burnout Inventory, job demands-resources model, occupational health, work environment, burnout prevalence, predictors of burnout, machine learning prediction models, linear regression, extreme gradient boosting, random forest, support vector regression, artificial neural networks, Sustainable Development Goals
Open Access status: green
OpenAlex ID: W7220548787
