<![CDATA[Understanding how students learn is key to making education more effective. This research presents an innovative, automated method for identifying students’ learning styles using artificial intelligence. This research employed the Felder–Silverman Learning Style Model (FSLSM), which examines how students process information, prefer input (visual or verbal), and comprehend concepts. Instead of asking students to fill out long forms every time, this study trained a Q-Learning agent, a type of reinforcement learning, to recognize learning patterns directly from questionnaire data. This study tested this approach using data from 799 students from various universities in Indonesia. The results showed that the model could accurately predict learning styles in almost every case, particularly in how students process and understand information. In a follow-up test with 50 students, the model achieved 100% accuracy, matching traditional FSLSM assessments perfectly. This demonstrates that Q-Learning can be a powerful tool for automatically identifying learning styles. It opens up new possibilities for creating personalized and adaptive learning systems that adjust materials and methods based on each student’s unique style. Moving forward, the system can be improved to better handle cases where certain learning styles are underrepresented]]>
Copyrights © 2025
