Detection of Depression among Nigerians using Machine Learning Techniques

Adegoke, Adedeji (2019) Detection of Depression among Nigerians using Machine Learning Techniques. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (2MB) | Preview

Abstract

Depression has always been a cause for concern in Nigeria and a dreadful entity that contributes to suicide rate among the young and the old in the country. In other to reduce the suicide rate and observed the depressive state of Nigerians on Twitter, this research project was tailored towards help highly skilled psychologists in the Nigeria health sector to detect depression among Nigerians. In this research project, various features were used to train different machine learning models in order to detect depression among Nigerians. The best model was a regularized generalized linear model using term frequency inverse document frequency and normalized data with a precision of 0.89, recall of 0.91 and f-measure of 0.90 which will be used by highly skilled psychologist in this domain to identify and detect depressive Nigerians on twitter. From the literature, class imbalance of dataset was dealt with synthetic sample which diminished the recall of their models, but the gap was breached by introducing tweets with positive polarity from a different dataset because positivity in a text has no effect other than positivity. Classification method was used to classify the depressive and non-depressive tweets using various classifiers and regularized generalized linear model with term frequency inverse document frequency and normalized data performed brilliantly. This will help Nigerians a lot in other to curb sudden death and suicide rate among its citizen and reduce high death rate statistics due to depression according to the World Health Organization.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software R Medicine > RA Public aspects of medicine > RA790 Mental Health
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Dan English
Date Deposited:	17 Jun 2020 15:55
Last Modified:	17 Jun 2020 15:55
URI:	https://norma.ncirl.ie/id/eprint/4303

Actions (login required)

View Item