Scholarlink

E-learning has largely expanded the methodological and technical capabilities of the teacher. Electronic educational environments allow not only to design the teaching material, but also to organize the testing of mastering the discipline, including, in an automated way. Another advantage of such environments is the storage of data on grades and other parameters of student learning. This allows to conduct diverse data analysis. In this paper, we analyze the data on student academic performance in an e-learning course in order to identify different learning styles. We applied k-means clustering method to identify students with similar learning strategies. Knowing the student’s preferences allows to individualize the learning process and develop learning strategies for each individual student based on their specific characteristics. #COMESYSO1120.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Clusterization of Students by Learning Styles: K-means Clustering

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Sadaquat Ali,
  • Oleg Ikonnikov,
  • Ivana Roncevic,
  • Vitaliy Grinchenko,
  • Natalia Vasilyeva,
  • Mareks Parfjonovs,
  • Roman Tsarev

摘要

E-learning has largely expanded the methodological and technical capabilities of the teacher. Electronic educational environments allow not only to design the teaching material, but also to organize the testing of mastering the discipline, including, in an automated way. Another advantage of such environments is the storage of data on grades and other parameters of student learning. This allows to conduct diverse data analysis. In this paper, we analyze the data on student academic performance in an e-learning course in order to identify different learning styles. We applied k-means clustering method to identify students with similar learning strategies. Knowing the student’s preferences allows to individualize the learning process and develop learning strategies for each individual student based on their specific characteristics. #COMESYSO1120.