Predictive Analysis Of Student Stress Level Using Machine Learning

Information Science and Engineering

College students are struggling with a lot of mental health issues, including stress, somatization, obsession, interpersonal sensitivity, depression anxiety, hostility, fear, paranoia, and psychopathy, which might have bad effects on them. The mental health problems of college students not just directly impact their development, but also affect the stability of campus. Most colleges pay more attention to students' crisis monitoring and prevention. All colleges just analyze whether students have mental health problems or what problems they are having. Some lectures doing manual counselling sitting with students and trying to identify mental health disorders for low academic performance. These systems cannot find hidden relationships in psychological data. We need a system to handle student mental health issues; here, we mainly emphasize student stress prediction. Many factors connected to stress like age, gender, workload, assignments, family issues, friend’s problems, attendance, teaching, etc…. Machine learning is a discipline that predicts the future based on past data. By using machine learning techniques, we predict student stress and levels, and the proposed system would offer recommendations based on students' stress levels. In this proposal system, we are developing automation for the education sector to predict student stress and levels. The proposed system is a browser-based application for colleges using Microsoft technologies such as Visual Studio, C#, and SQL Server.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.