ระบบแนะนำด้วยการเรียนรู้ของเครื่องโดยใช้รูปแบบการเรียนรู้แบบวีเออาร์เคและโคล์บ สำหรับวิชาเอกที่เกี่ยวข้องกับดิจิทัล ของมหาวิทยาลัยในเชียงใหม่

Abstract

This study aims to develop a digital field recommendation system by classifying students' learning styles based on the VARK and Kolb models. The system uses the Support Vector Machine (SVM) algorithm to determine students' suitability for digital fields, with the goal of providing personalized educational recommendations. The study's results show that data variation significantly impacts the accuracy of the classification model. Modifying the data format reveals promising approaches with notable classification accuracy. The development of the digital field recommendation system for high school students received positive feedback from those who tested it. Most students expressed satisfaction with the system, with average satisfaction scores ranging from 3.2 to 4. In particular, the system's ability to recommend suitable digital fields (average score 4) and the recommendation for others to use the system (average score 3.92) were highly appreciated. The survey results indicate that the system has the potential to be effectively implemented in the educational system to assist students in making informed decisions about their field of study.