Acceso usuarios
Jiao Zhang, Fariza Khalid, Hazrati Husnin
Data mining techniques can deeply analyze students’ behavioral data, grade data, and feedback during the process of learning C-STEAM courses. Through complex algorithm models, accurately identify students’ learning difficulties, interests, and personalized needs. This article explores how to use data mining techniques to optimize the content design of C-STEAM courses. Utilize data mining techniques to identify the learning needs and interests of different students, and achieve personalized customization of course content. Discover the relationship between student grades and specific learning resources through association rule mining, and recommend suitable learning materials for different students. The cumulative variance interpretation rate after rotation is 61.717%, exceeding the threshold of 50%. Through data mining of learners’ after-school test scores, we found a certain correlation between course content and learner performance. Learners have higher average exam scores in certain course content modules, while others have relatively lower scores.
