Optimizing Well-Being: Unveiling Eustress and Distress through Machine Learning

The predicament of rising stress levels among college students has increased rapidly, and its severe implications have caused numerous problems, such as notable anxiety, high blood pressure, increased cortisol levels, suicidal thoughts, and different health issues. This study addresses these issues found among college students by implementing machine learning algorithms like Decision Trees, Random Forest, Support Vector Machines, AdaBoost, Naive Bayes, Logistic Regression, and K-nearest Neighbors. The primary outcome of this work is to leverage a research study to predict and mitigate both the Eustress and Distress based on the collected questionnaire dataset. We conducted a workshop with the primary goal of studying the stress levels found among the students. This workshop was attended by students whose ages ranged between (18-21) years old, numbering about 800. A questionnaire was given to the students, validated under the guidance of the experts from All India Institute of Medical Sciences (AIIMS) in Raipur, Chhattisgarh, India, on which our dataset is based. The survey consists of 28 questions, aiming to comprehensively understand the multidimensional aspects of stress, including emotional well-being, physical health, academic performance, relationships, and leisure. The research finds that K-Nearest Neighbors has a maximum accuracy for Eustress, reaching 93%, and for Distress, the Logistic Regression has a maximum accuracy of 99%. The study contributes to a deeper understanding of stress determinants. It aims to improve college students' overall quality of life and academic success, addressing the multifaceted nature of stress.