Machine Learning Algorithms for Detecting Mental Stress in College Students

TL;DR

The paper tackles detecting mental stress in college students using a questionnaire-based, cost-efficient approach that avoids costly physiological sensors. It compares seven classifiers—Decision Trees, Random Forest, Support Vector Machines, AdaBoost, Naive Bayes, Logistic Regression, and K-Nearest Neighbors—on a 28-item survey dataset from 843 students and finds Support Vector Machines to deliver the best stress-classification performance with up to 95% accuracy. The study demonstrates the viability of psychological-data–driven stress detection for early interventions and student well-being, and it provides a clear workflow from data collection to model evaluation, including 5-fold cross-validation and standard metrics. Looking forward, the authors plan to scale the dataset, incorporate multimodal wrist-worn sensor data, and apply deep learning to further improve granularity and impact, with open-source code available on GitHub.

Abstract

In today's world, stress is a big problem that affects people's health and happiness. More and more people are feeling stressed out, which can lead to lots of health issues like breathing problems, feeling overwhelmed, heart attack, diabetes, etc. This work endeavors to forecast stress and non-stress occurrences among college students by applying various machine learning algorithms: Decision Trees, Random Forest, Support Vector Machines, AdaBoost, Naive Bayes, Logistic Regression, and K-nearest Neighbors. The primary objective of this work is to leverage a research study to predict and mitigate stress and non-stress 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 Approximately 843 students aged between 18 to 21 years old. A questionnaire was given to the students validated under the guidance of the experts from the All India Institute of Medical Sciences (AIIMS) 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. This work finds that Support Vector Machines have a maximum accuracy for Stress, reaching 95\%. The study contributes to a deeper understanding of stress determinants. It aims to improve college student's overall quality of life and academic success, addressing the multifaceted nature of stress.

Figures (5)

• Figure 1: Overall Architecture of the Proposed Work
• Figure 2: Heatmap of the Dataset Attributes
• Figure 3: Architecture of Data Preprocessing Workflow
• Figure 4: Confusion Matrix (Left) and ROC Curve (Right) for Stress Classification
• Figure 5: Comparing several machine learning models for Stress Classification