Decision Support System for Identifying Student Learning Styles in Elementary School using Naïve Bayes Algorithm

Abstract

Identifying student learning styles is essential for teachers to design effective and adaptive teaching strategies. At SDN Rejoagung 3, this process is currently conducted manually through observation and interviews, which are prone to subjective bias. This research develops a web-based decision support system to classify student learning styles—Visual, Auditory, and Kinesthetic—using the Naïve Bayes algorithm. The system was built using data collected via questionnaires from students in grades 1 to 6. Testing was conducted using a confusion matrix to evaluate the model's performance. The results show that the Naïve Bayes algorithm successfully classified learning styles with an accuracy of 94.12%. This system provides a more objective and systematic tool for teachers to identify students' preferences, enabling more personalized instructional delivery in an elementary school context