Mining Moodle Data to Detect the Inactive and Low-performance Students during the Moodle Course

• DOI: 10.1145/3291801.3291828
• Publication Date: 2019-01-14T13:15:25Z
• Authors: Mushtaq Hussain; Sadiq Hussain; Wu Zhang; Wenhao Zhu; Paraskevi Theodorou; Syed Muhammad Raz...
• Keywords: Learning Management; Course (navigation); Virtual learning environment

In web-based learning systems such as massive open online course (MOOC) and modular object-oriented developmental environment (Moodle), monitoring the student's activities well predict low-performance students is an important task because it enables instructors to award when their level drops from normal levels having lower grades. We used several machine (ML) classification clustering techniques extract pattern student data during completing Moodle course; which instructor detect in advance before examination. The experimental result shows that fuzzy unordered rule induction algorithm (FURIA) technique achieves high accuracy detecting inactive predicts different categories of course. K-means also able group active users poorly performed users. demonstrates our proposed system will be easily integrated send alert low- performance while build efficient education for students.