DSpace Repository

Depression prediction among student based on their daily activities

Show simple item record

dc.contributor.author Pranty, Miskatun Ahmed
dc.date.accessioned 2024-08-21T03:56:14Z
dc.date.available 2024-08-21T03:56:14Z
dc.date.issued 2024-01-25
dc.identifier.uri http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/13183
dc.description.abstract Depression affects most people in modern life. Inadequate treatment even leads to many people taking their own lives. Early detection and treatment of depression in patients are very easy to achieve. We are unable to make the finest decision at the right moment since we are unaware of the severity of the depression. The foundation of a nation is its pupils. Students educate and better their nation, representing it to the outside world. A number of things, including the difficulties Bangladeshi teenagers face in their schooling, contribute to depression. Our study's goals are to ascertain the frequency of depressed symptoms, the factors that contribute to them, and methods for lowering depression among college students. In this study, an online student depression dataset have been used for predicting the depressed or not. Two class have been consisting this dataset. Multiple algorithms have been run on this data. and have reached the maximum level of precision. This initiative will assist us in determining depression levels. To determine their degree of despair, we employ a form of algorithm. Five algorithms have been selected for this study. XGBoost classifier, Random Forest algorithm, SVM, Naive Bayes, and Decision Tree classification are among them. The forecast made by the XGBoost classifier performs the best overall. The algorithm that yields the greatest results for this research is 98.70% en_US
dc.publisher Daffodil International University en_US
dc.subject Machine Learning en_US
dc.subject Mental Health en_US
dc.subject Behavioral Analysis en_US
dc.subject Student Well-being en_US
dc.subject Predictive Modeling en_US
dc.title Depression prediction among student based on their daily activities en_US
dc.type Other en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Browse

My Account