A Predictive of Student's Interest in Game Learning Using Data Mining Techniques

The purpose of this research is to create a model that predicts learners' interest in gaming-based learning using data mining techniques. The study involved 304 students from the Business Computer Program at Suphan Buri Vocational College, Thailand. Using the Rapid Miner Studio (version 10.3.001) and a decision tree algorithm, the research classified students' interest based on their gaming habits, study experience with games, and academic performance. Results revealed that students who enjoy playing games, have studied using games, and have not passed all subjects are more likely to be interested in gaming learning. In contrast, those who passed all subjects are less interested. The model's accuracy, evaluated by splitting the data into training (70%) and testing (30%) sets, was 86.81%. These findings can inform the development of educational games to enhance classroom interaction, improve cognitive and affective skills, and stimulate learners' interest in innovative learning methods.