Human Tension Screening Using Sleeping Behavior Using Machine Learning Algorithms

Tension, also known as Tensionors, refers to a psychological or emotional state triggered by stressful or unavoidable situations. Understanding an individual’s tension levels is essential for preventing potential negative outcomes in life. Sleep disturbances are closely linked to various physical, psychological, and social challenges. The primary aim of this study is to explore how human tension levels can be detected using machine learning algorithms, based on sleep-related behavioral patterns. The dataset used includes multiple features related to sleep behavior and corresponding tension levels. To perform the classification, six machine learning models were applied: Multilayer Perceptron (MLP), Random Forest, Support Vector Machine (SVM), Decision Trees, Naïve Bayes, and Logistic Regression. After preprocessing the data, these models were evaluated to identify the most effective one. Among them, the Naïve Bayes algorithm demonstrated superior performance, achieving an accuracy of 91.27%, along with high precision, recall, and F- measure values. It also recorded the lowest Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE). The findings of this study suggest that it is feasible to estimate human tension levels through sleep behavior data, allowing for early intervention and management of related issues.