Abstract

Currently, mental stress is a prevalent issue, particularly among the younger generation. The age group that was previously associated with joy and excitement is now struggling with high levels of stress. This rise in stress levels is linked to a range of problems such as depression, suicide, heart attacks, and strokes. Our aim is to minimize stress levels among students by enabling them to identify the factors causing stress. The impact of exam or test-related stress on students is significant, yet it often goes unnoticed. Other factors that contribute to internal stress among students include family pressure, peer pressure, health problems, and financial circumstances. The COVID-19 pandemic has only added to this cumulative stress, disrupting students' normal lives and exposing them to further pressure, resulting in underperformance. The use of modern technologies such as Machine Learning or data science techniques for managing student stress in educational institutions has been limited. Monitoring each student's profile and stress level is a significant task that typically falls on the mentor or counsellor of the institution. Our work aims to automate stress prediction for each student based on various parameters and provide the results to each student accurately using Machine Learning techniques. By monitoring each student's stress levels and addressing them promptly, we can enhance their performance in the institution. Students are classified as stress-free or stressful, and if they are stressed, their stress range is predicted. Based on this range, doctors can provide each individual with personalized results and advice.

Description