Web-based mental health predicting system using K-Nearest neighbors and XGBoost algorithms

Zulkefli, Nurul Farhanaa, Diah, Norizan Mat, Ismail, Azlan, Mohamed Hanum, Haslizatul Fairuz, Ibrahim, Zaidah and Arif, Yunifa Miftachul ORCID: https://orcid.org/0000-0002-2183-0762 (2023) Web-based mental health predicting system using K-Nearest neighbors and XGBoost algorithms. Presented at IVIC'23 - 8th International Visual Informatics Conference 2023, 15-17 Nov 2023, Bangi, Malaysia.

Text 16024.pdf - Published Version Restricted to Repository staff only Download (2MB)

Abstract

Problems with mental health are common presently and have been a worry for a long time. Mental health problems, like anxiety, depression, and panic attacks, can be caused by numerous things. Therefore, recognising the start of men- tal disease is becoming increasingly crucial to maintaining a good life balance. This study uses machine learning to identify any possible mental health disor- ders in an individual to attain this goal. The investigation employed supervised machine learning to predict mental health status, namely K-Nearest Neighbors (KNN) and XGBoost, with performance evaluation criteria including accuracy, precision, recall, and F1 score. When these two algorithms were compared, it was discovered that XGBoost produced a more effective prediction model, which was then employed to develop a web-based mental health prediction system. The web- based method creates a questionnaire for mental health issues. Based on the user’s responses to the questions, the system will predict his or her mental health status as normal, depression, anxiety, stress, loneliness, or regularity. Every component of the system, including buttons and forms, has been successfully tested using functionality tests. Moreover, the system’s advantages, weaknesses, and future study directions are identified.

Item Type:	Conference (Paper)
Keywords:	K-Nearest neighbors; mental health; predicting; XGBoos
Subjects:	08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing
Divisions:	Faculty of Technology > Department of Informatics Engineering
Depositing User:	Yunifa Miftachul Arif
Date Deposited:	03 Nov 2023 10:22

Downloads

Origin of downloads

Actions (login required)

View Item