An Approach to Determine and Categorize Mental Health Condition using Machine Learning and Deep Learning Models

Abstract

The mental health of the human population, particularly in India during and after the COVID-19 pandemic is a major concern. All age groups have undergone mental stress during and after COVID-19, especially college students in urban areas and individuals belonging to the age group from 16 to 25. Early detection of mental stress among urban students will help in the resolution of major related issues that may hurt one's career. Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) have enabled the prediction of mental health status. Numerous studies have been conducted using various approaches, but there is still no agreement on how to predict mental symptoms across age groups. In the current study, proposed DL, Long Short-Term Memory (LSTM), and ML models, namely Support Vector Machine (SVM), ADA Boost, Random Forest (RF), K-Nearest Neighbor (K-NN), Logistic Regression (LR), and Multi-Layer Perceptron (MLP) are trained and tested on a real-world dataset. The DL LSTM model outperformed the conventional ML models with an accuracy of 100%.

Keywords

• mental health
• machine learning
• health status detection
• mental health data