Academic stress detection based on multisource data: a systematic review from 2012 to 2024

The field of academic stress detection has gained significant attention recently because mental and physical health is crucial for academic success. The goal of academic stress detection is to identify a student's level of stress during the learning process using observable markers including physiological, behavioral, and psychological data. In recent years, detection methods that utilize wearable and nonwearable sensors have gained increased attention owing to their rich functionalities. In order to discover contemporary developments, coping strategies, limitations, difficulties, and potential research areas for addressing academic stress in educational settings, this study conducted an exhaustive review of the existing literature. First, we discussed how stressful events influence students' psychological and physical health as well as the statistics frequently utilized to monitor academic stress. Then, using machine learning and deep learning methods, we described academic stress detection models. In addition, we described self-regulated strategy, computer-supported strategy and interactive learning technology-supported strategy. This comprehensive analysis of the latest techniques and recommendations for potential research avenues for tackling academic stress in educational settings will help other researchers in this field carry out and assess user research and build academic stress detection systems.