A MACHINE LEARNING APPROACH FOR STRESS DETECTION IN IT EMPLOYEES

The IT sector has a serious and widespread issue with stress. It has negative effects on workers' mental and physical health, which in turn lowers productivity, increases absenteeism, and decreases retention rates. Consequently, a system that can automatically identify IT workers' stress levels and provide necessary solutions is required. The goal of this project is to create a stress detection system for information technology workers by using machine learning methods. The best attributes were used to pick the suggested system using ML. Several machine learning techniques, such as decision tree (DT), support vector machine (SVM), logistic regression (LR), and Naive Bayes (NB), were used to conduct the categorization. Using a dataset of IT personnel, we will conduct experiments to assess the performance of the proposed solution. We will evaluate several ML models by comparing their F1-score, recall, accuracy, and precision. Additionally, we will look at what causes stress in IT workers and evaluate the characteristics that help with stress detection the most. Early intervention for stressed IT workers