Scholarlink

This paper presents research on data mining and visualization methods that analyze, in real time, learners’ clicks on educational materials during both large face-to-face classes and online distance learning classes with large participants. The purpose of this paper is to research how learning logs collected using online materials on the Moodle LMS can be used to enhance lesson delivery and analyze learning patterns. To achieve this, we developed a real-time visualization method that identifies inappropriate learning behaviors by conducting time-series analysis of learning logs, classifying participant material clicks, and simultaneously detecting outliers. We confirmed that the proposed method can be used in regular classroom settings and provided concrete examples demonstrating its potential to support teachers’ decision-making.

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

Real-Time In-Class Data Mining of Moodle Click Logs for Learning Pattern Classification and Outlier Detection

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Konomu Dobashi,
  • Curtis P. Ho,
  • Catherine P. Fulford,
  • Christina Higa,
  • Kris Hara

摘要

This paper presents research on data mining and visualization methods that analyze, in real time, learners’ clicks on educational materials during both large face-to-face classes and online distance learning classes with large participants. The purpose of this paper is to research how learning logs collected using online materials on the Moodle LMS can be used to enhance lesson delivery and analyze learning patterns. To achieve this, we developed a real-time visualization method that identifies inappropriate learning behaviors by conducting time-series analysis of learning logs, classifying participant material clicks, and simultaneously detecting outliers. We confirmed that the proposed method can be used in regular classroom settings and provided concrete examples demonstrating its potential to support teachers’ decision-making.