Extracting the Hidden Patterns Affecting Mental Health through Data Mining Techniques

Abstract

Background and Objective: This study was conducted to shed light on the hidden relationships, trends, and patterns of the teenagers’ mental health dataset based on data mining techniques.
Materials and Methods: The proposed method has four parts as follows: data preprocessing, data cleaning, target class selection, and extracting rules. The classes included inappropriate, moderate, and acceptable. The rules were extracted separately by implementing ID3, CHAID, and rule induction on the Caspian 5 dataset.
Results: It was found that the teenagers who rarely drink carbonated soda and have dinner seven days a week, have acceptable status of mental health. Besides, watching TV and playing computer games for 4 hours or more per week, drinking tea and packaged juices, eating cakes, cookies, pastries, biscuits, and chocolate weekly  could lead to inappropriate status of  mental health.
Conclusion: An attempt to improve health especially in youth is one of the important concerns of every country.  The rules express the negative impact of soda on mental health. Besides, it can be concluded that there is a direct relationship between having breakfast and mental health.

Keywords: Mental Health, Data Mining, Hidden Pattern, Iterative Dichotomiser 3(ID3)