Pokhrel, Sangita ORCID: https://orcid.org/0009-0008-2092-7029, Ganesan, Swathi ORCID: https://orcid.org/0000-0002-6278-2090, Ling, Soonleh ORCID: https://orcid.org/0000-0002-7104-3812 and Somasiri, Nalinda ORCID: https://orcid.org/0000-0001-6311-2251 (2025) Understanding the Behaviors and Detecting the Mental Health Symptoms Among Students Using Machine Learning Algorithms. In: Raj, G., Unhelker, B. and Choudhary, A., (eds.) Advances in Artificial Intelligence and Machine Learning. Lecture Notes in Electrical Engineering (1264). Springer, pp. 13-30

Full text not available from this repository.

Abstract

International students studying in the UK are facing challenges in their life that can impact their mental health. To better understand and address these challenges, this research paper investigates the behaviors of the students and the potential machine learning algorithms to predict the mental health of them. A form was distributed to international students at various universities in the UK. The survey aimed to gather information on aspects like age, country of origin, sleep patterns, emotional behaviors, support from family and the university, financial pressures, experiences of loneliness, and living standards, all in an effort to gain insights into their mental well-being. The collected data has been cleaned, pre-processed, and visualized the findings such as whether male or female are affected much based on the collected data, their sleeping behavior, financial stress, and so on. Later, machine learning algorithms such as decision tree, CatBoost, random forest, and XGBoost classifiers were used to predict the mental health status of the students, and the random forest works best with 88% accuracy with the highest precision of 0.92 and F1-score of 0.82. The findings from this research have the potential to offer valuable perspectives and assistance in improving mental health services for international students in the UK. By using machine learning algorithms, this study aims to improve upon traditional methods of mental health prediction and provide a more efficient and accurate means of identifying and supporting students in need.

Item Type:	Book Section
Status:	Published
DOI:	10.1007/978-981-97-9507-9_2
School/Department:	London Campus
URI:	https://ray.yorksj.ac.uk/id/eprint/11903

University Staff: Request a correction | RaY Editors: Update this record