Implementasi Gated Recurrent Unit (GRU) dalam Prediksi Gangguan Mental Health pada Mahasiswa“Fakultas Ilmu Komputer dan Teknologi Informasi Universitas Sumatera Utara

Abstract

Mental health is a crucial aspect of individual well-being that includes emotional, psychological and social balance. In recent years, attention to mental health among university students has increased significantly. Students face various pressures, such as academic demands, financial problems, and social adaptation, which can have a negative impact on their mental health. This study aims to predict mental health disorders in students of the Faculty of Computer Science and Information Technology, University of North Sumatra using the GRU (Gated Recurrent Unit) algorithm. The data used in this study were collected through Google Form as much as 645 data. The GRU method was chosen because of its ability to make predictions. The types of diseases that will be predicted in this study are anxiety and depression. This research process involves training the GRU model and inputting it into Flask. The epoch used is 50, the learning rate is 0.001, and the batch size is 8. The dataset collected through Google Form then goes through a preprocessing stage, including column conversion to numeric type and removing empty values, before the training and evaluation process. The results of this study show that the mental disorder prediction analysis method using the GRU algorithm provides significant accuracy, reaching an accuracy of 96%. This result shows the ability of GRU in predicting mental health disorders.