• ishfaq majeed rather
• Dr. Simmi Dutta
• Mr. Prabjot Singh

Depression is a serious psychological health problem that can disrupt a person’s emotional well-being. In this contemporary world mental stress has emerged as a significant concern, particularly affecting students who were once perceived as carefree. Escalating stress levels among students have been linked to many issues like depression, suicide, heart attacks, and strokes. Detecting students' depression early is very important nowadays which is the primary objective of this research paper. This research focuses on evaluating depression experienced by college students, using the depression scale questionnaires (PHQ 9). Data was collected from 300 students of the GCET Jammu. They were questioned simply about how they felt in situations they might have encountered within the previous two weeks. Their answers are given some amount of weight that helps to calculate a score to analyze the depression level of students. There are five machine learning algorithms (MLA) that are used: Support Vector Machine (SVM), Decision tree (DT), k-nearest neighbor (KNN), Random Forest (RF), and Naïve Bayes (NB). We have also utilized performance evaluation with a confusion matrix in this work. The results show that, when compared to other algorithms, SVM provides the highest accuracy of 94.8%.

Depression, Machine Learning, Performance Evaluation

"predicting depression using machine learning algorithms", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 10, page no.f13-f21, October-2023, Available :http://www.jetir.org/papers/JETIR2310503.pdf

"predicting depression using machine learning algorithms", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 10, page no. ppf13-f21, October-2023, Available at : http://www.jetir.org/papers/JETIR2310503.pdf