Mental Health Analysis: ML And Explainable AI Predict Depression Among Bangladeshi University Students

This paper uses Machine-learning and Explainable AI techniques to investigate the prevalence of depression and its determinants among the Bangladeshi university students.Because of a variety of socioeconomic and cultural factors, young adults are disproportionately affected by depression, a common mental health issue.The study examines depression rates and contributing factors among Bangladeshi students across 39 features by utilizing a Kaggle dataset with 1,977 data points.With careful feature engineering and preprocessing, an improved dataset with eighteen columns was produced.Subsets of the dataset were used for training, testing, and validation of the models; among the evaluation metrics, the ensemble model that combines Support Vector Machine (SVR) and Linear Regression proved to be the most effective.Notably, when compared to individual ML models, the ensemble model performed better.The results emphasize how important it is to address depression in university settings with early detection and intervention techniques.All things considered, this study advances the field of mental health analysis and highlights the potential of machine learning and explainable artificial intelligence in detecting and treating mental health issues in young adults.