A Novel Approach to Detect Human Depression Using Machine Learning Algorithms

Date
2022
Student ID
Editor
Journal Title
Volume
Issue
Journal Title
Journal ISSN
Volume Title
Abstract
is a serious condition that affects a person's way of life and interferes with normal functioning. In impoverished and developing nations, depression is particularly common among young people. Youth in nations like Bangladesh struggle with schoolwork, employment, relationships, drug use, and family issues, all of which are important or minor contributors on the road to depression. A machine learning (ML) model for the prediction of human depression was to be developed as part of this study. An openly accessible dataset on depression was used in the study. There are 1521 individual records in the collection. The effectiveness of seven machine learning algorithms for the purpose of forecasting depressive symptoms was evaluated. The goal of this study is to look at depressive symptoms using machine learning to increase efficiency and accuracy. It has an excellent union of feature selection approaches and classifiers by studying the combinations of the most prominent feature selection techniques and classifiers, such as K Nearest Neighbors (KNN) Classification, Decision Tree (DT) Classification, Logistic Regression (LR), Random Forest (RF), Ada Boost (AB), Support Vector Machine (SVM) and Gradient Boosting (GB). The Random Forest classifier was found to be more accurate than any other model with 94 percent accuracy. A lot of the models used in this study are more accurate than the models used in previous studies, which means that the models are more trustworthy. Overall, the study showed that machine learning models are effective in predicting human depression and are a useful tool for locating and predicting the related risk variables that affect mental health. The use of machine learning models for youth depression screening and early detection may make it easier to create health prevention and intervention programs that will improve the mental health of young people in low and middle-income nation.
Description
Keywords
Citation
Department Name
Electrical and Computer Engineering
Publisher
North South University
Printed Thesis
DOI
ISSN
ISBN