<![CDATA[Mental health issues in the workplace have become an increasingly important concern, particularly in the high-pressure environment of the information technology industry. This study aims to evaluate the impact of feature selection based on interviews on the performance of machine learning models in classifying mental health disorders. The dataset used is sourced from Open Sourcing Mental Illness (OSMI), which consists of various features related to employees' mental health conditions, previously used without feature selection in prior research. Through an interview with an experienced Human Capital professional with a psychological background, relevant features were selected based on domain expertise. Subsequently, machine learning models, namely Random Forest and XGBoost, were trained using two scenarios: without feature selection and with feature selection. The results of the study indicate that feature selection based on interviews can improve model accuracy by 1.67% for Random Forest and 0.67% for XGBoost. These findings emphasize the importance of integrating psychological insights into the data processing to produce more relevant and efficient models. This research provides practical contributions to assist companies in implementing early detection of mental health disorders effectively.]]>
Copyrights © 2024
