Mental Stress Detection Using Machine Learning

• Author(s): Dinesh A ; Bhalanath Mohanta ; Byrava M ; Humaun Forhat
• Paper ID: 1707576
• Page: 1042-1045
• Published Date: 25-03-2025
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 8 Issue 9 March-2025

Abstract

This paper pivots on detecting mental stress levels among employees and students using a machine learning model called the Random Forest Classifier. A dataset from Kaggle, based on employees and students and emotional responses to various questions, was used to calculate stress scores. The model is focused to achieve 100% training accuracy and 95% test accuracy, proving its reliability. A web application was developed using Flask, where user answer the questions, and the system predicts their stress levels. This non-invasive tool can help identify high-stress individuals early, enabling timely support and promoting mental health. This project aims to foster well-being in the society through technology-driven solutions. By leveraging machine learning, it promotes mental health support within society, fostering a health.

Keywords

Machine Learning, Mental Stress Detection, Random Forest Classifier.

Citations

IRE Journals:
Dinesh A , Bhalanath Mohanta , Byrava M , Humaun Forhat "Mental Stress Detection Using Machine Learning" Iconic Research And Engineering Journals Volume 8 Issue 9 2025 Page 1042-1045

IEEE:
Dinesh A , Bhalanath Mohanta , Byrava M , Humaun Forhat "Mental Stress Detection Using Machine Learning" Iconic Research And Engineering Journals, 8(9)