Classification of Student Learning Styles Using the Naïve Bayes Method (Case Study: STMIK Kaputama)

Each student has unique characteristics in absorbing, processing, and retaining information, which is known as learning style. Understanding learning styles is very important so that students can optimize their learning methods. This study aims to build a web-based expert system that is able to classify students' learning styles at STMIK Kaputama using the Naive Bayes Classifier method. This system classifies students into 7 (seven) categories of VAK (Visual, Auditory, Kinesthetic) model combinations based on 10 questionnaire question indicators. The classification model is built by referring to a knowledge base consisting of 35 training data. Based on the results of the system's performance test using the Confusion Matrix on 5 new test data, the Naive Bayes algorithm has proven to be very reliable in predicting learning styles with an accuracy level of up to 100%. In addition, the evaluation metrics of Precision, Recall, and F1-Score as a whole also obtained a perfect score of 100%. Thus, this system is feasible to be implemented to help students recognize the potential of their learning styles independently.