Unveiling Mental Stress: Examining the Impact on College Students' Well-being Using Machine Learning Based Solutions

This study examines the growing mental stress problem, especially among young adults, emphasizing college students' stress levels before tests and online. It explores the effects of variables like test pressure and recruitment stress, frequently disregarded, and assesses stress throughout various life phases. It also aims to establish a correlation between stress and internet usage frequency to comprehend its impact on students' mental health. To identify mental diseases and their applications, the study uses a variety of machine learning (ML) techniques, such as Decision Tree (DT), Random Forest (RF), Logistic Regression (LR), Hist Gradient Boosting (HGB), and K-nearest neighbors (KNN). The paper explores the features of both supervised and unsupervised machine learning algorithms and provides an overview of each. The findings show that DT has the highest accuracy, with a 91% accuracy rate, closely followed by RF and LR, with 90% accuracy. KNN and HGB, on the other hand, show somewhat lower accuracy levels of 88% and 89%, respectively. This study clarifies the dynamics of mental health among college students and provides information on how to use ML techniques for mental health diagnosis and treatment.