Real Time Identification of Students’ Stress Factors using Machine Learning Techniques

Students’ stress is a significant concern impacting academic performance and well-being of students across the globe. By leveraging machine learning techniques, this research aims to develop a robust model capable of accurately identifying stress factors amongst students. For this research, the initial dataset was taken from Kaggle. However, to enhance the dataset’s diversity and relevance, additional samples were collected directly from students and combined with the original dataset. In this work, different machine learning models have been used for comprehensive stress detection which were evaluated using different performance metrics. Further, a novel interactive interface was developed to provide students with a real time, personalized stress detection experience. The system also provides recommendations based on the detected stress level. This research not only enriches the dataset but also provides machine learning enabled interface to tackle the concern of the students.