Abstract—The risk of depression in youth affects future development of the learning process. Therefore, it is important to study on preventing the risk of depression in youth. The purpose of this research was (1) to study the risk situation of youth’ depression in Thailand, and (2) to develop a model for predicting depression among youth in Thailand. The data used in the research were 1,413 samples from 9 faculties at the Rajabhat Maha Sarakham University, and Phadungnaree School at Mueang District of Maha Sarakham Province, Thailand. Research tools and procedures used were the data mining principles to analyze and develop prototype models. It includes the decision tree, naïve bayes, and artificial neural networks techniques. The results showed that the majority of the respondents had no depressive risk conditions with 1,059 samples (74.95%). However, there are still three risk groups that need to be monitored: mild level with 260 samples (18.40%) moderate level with 78 samples (5.52%), and severe level with 16 samples (1.13%). The observations were taken to develop a prototype model. It was found that the highest accuracy model was the artificial neural networks technique with an accuracy value of 97.88%. Based on such success, the researchers hope to develop a future application in preventing youth’ risk depression.
 

Index Terms—predictive model, depression risk analysis, learning analytics, machine learning
 

Cite: Wongpanya S. Nuankaew, Patchara Nasa-ngium, Prem Enkvetchakul, and Pratya Nuankaew, "A Predictive Model for Depression Risk in Thai Youth during COVID-19," Journal of Advances in Information Technology, Vol. 13, No. 5, pp. 450-455, October 2022.

Copyright © 2022 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.