Predicting Academic Stress Among Students Through Psychometric Assessments Using Hybrid Neural Networks

Academic stress and incivility harm college students' mental health. Mitigating these impacts requires understanding moderating factors. Yoga is often used to reduce stress, but little is known about how it affects students' mental health. Sentiment categorisation also employed SAE-LSTM, a hybrid machine learning model. SAE was used for feature extraction and LSTM for classification. Due to academic stress and incivility, 65% of students reported depression. The SAE-LSTM model classified mental health disorders with 96.67% accuracy, outperforming typical machine learning methods. These findings show that deep learning works in mental health evaluation. Academic stress and incivility greatly harm students' mental health, according to this study. As a psychological buffer, gratitude may reduce stress. The SAE-LSTM model also accurately classifies sentiment, providing mental health monitoring insights. This approach should be used in real time for stress detection and intervention in future studies.