Classification of Employee Mental Health Disorder Treatment with K-Nearest Neighbor Algorithm

Abstract

Mental health problems are increasingly crucial in the workplace. These issues affect employee productivity and accordingly it affects the company's prolificacy. To minimize mental health issues among employees, companies must identify factors related to employee's mental health. Therefore, a classification method to find out whether an employee requires mental health treatment or not is highly much-needed. This paper seeks to develop the application of features selection using chi-square to the performance of the K-Nearest Neighbor (KNN) algorithm in conducting classifications. The stages carried out were: (1) collecting data obtained from Open Sourcing Mental Illness (OSMI), (2) data preprocessing process (data cleaning, feature selection, data transformation), (3) implementing the KNN algorithm in classifying the data, and (4) evaluation process to determine algorithm performance outcome using a confusion matrix which generates precision, recall, and accuracy values. The classification using the KNN algorithm obtained 87.27% of accuracy, 84.21% of precision, and 66.7% of recall. Accordingly, the resulting performance is more effective than previous research. The 2.27% increase in accuracy compared to the research conducted by Shruti Appiah in conducting classifications using Naive Bayes and SVM resulted in an accuracy of 66%. To sum up, data on mental health treatment is applicable for classification using KNN with a high degree of accuracy.