Mental Stress Detection of University Students in Bangladesh Using Machine Learning

Abstract

These days, there is a huge problem with mental stress, and the problem is particularly widespread among students at educational institutions of higher learning. According to the views that are prevalent now, the historical era that was formerly thought to be the one with the least level of stress is now deemed to be the most difficult time period. Depression, suicide, heart attacks, and strokes are just some of the current health issues that have been linked to the rising levels of mental stress that individuals are exposed to in today's culture. Because of this, we largely extracted the mental stress ratings of university students by using six distinct machine learning algorithms for this study. These examples of machine learning algorithms are as follows: Decision Tree Classifier, Random, Forest Classifier, SVC, KNN Classifier, Multinomial NB, and K-Nearest Neighbors Regressor. The major objective of this inquiry is to determine the number of students who are experiencing difficulties in managing with their emotional stress. The dataset was put together by hand with paper and manual information obtained from a survey. Out of the six different classification strategies, the Decision Tree Classifier and the Random Forest Classifier both had the highest test result of 0.99.