Machine Learning Techniques for Classifying Self-Regulated Learning of Secondary Students in Thailand
Main Article Content
Abstract
The objectives of this research were 1) to proposed the Machine Learning (ML) techniques for classifying students’ Self-Regulated Learning characteristics, and 2) to test Machine Learning (ML) techniques based on students’ Self-Regulated Learning characteristics. The research conducted by analyzing factors on Self-Regulated Learning theory, synthesize relevant Machine Learning (ML) techniques, and analyze data by using Frequency distribution and Machine Learning (ML) techniques. This research has given Human Ethics Approval (HE-RDI-NRRU.046/2565) in research conduction. The finding showed that, 1) the Decision Tree, Artificial Neuron Network, Naive Bayes, Logistic Regression, and K-Nearest Neighbors were the appropriated techniques to use as data analytics techniques for analyzing and enhancing learning based on students’ Self-Regulated Learning characteristics, 2) the most technique which gave the high efficacy is Decision Tree which researchers will use in development platform to predict Self-Regulated Learning of students in the future.