Prediction of Student's Wellbeing from Stress and Sleep Questionnaire data using Machine Learning Approach

A sound mental health has its benefits for the overall well-being of an individual. The decline in mental health conditions has a critical impression on other vital functionalities of the human system both psychologically and physiologically. And a student's well-being is largely contributed by the level of perceived stress and overall quality of nighttime sleep which might have evolved by various external factors over a while. The main objective of this study is to understand the correlation between Perceived Stress Scale (PSS) scores and Pittsburgh Sleep Quality Index (PSQI) global scores from StudentLife, a publicly available dataset over the period, and classify the well-being factor as 'Good' 'Average' and 'Bad' The linear regression model significantly demonstrated the association between PSS scores and Pittsburgh Sleep Quality Index (PSQI) scores. Machine Learning techniques like Decision Trees (DT), Support Vector Machine (SVM), and K-nearest neighbors(K-NN) were implemented on both Pre-Test and Post-test questionnaire data. While SVM resulted in better accuracy for Pre-test data, the K-NN classifier resulted in best accuracy for Post-test data, and the performance was evaluated using performance metrics like accuracy Precision, recall, and F1 score.