Digital Library

cab1

 
Title:      COMPARATIVE ANALYSIS OF CLUSTERING ALGORITHMS WITHIN A WEB-BASED LMS
Author(s):      Kyle E. De Freitas, Margaret Bernard
ISBN:      978-989-8533-39-5
Editors:      Ajith P. Abraham, Antonio Palma dos Reis and Jörg Roth
Year:      2015
Edition:      Single
Keywords:      Clustering, Educational Data Mining, Learning Management Systems, Web Usage Mining, Moodle
Type:      Full Paper
First Page:      11
Last Page:      18
Language:      English
Cover:      cover          
Full Contents:      click to dowload Download
Paper Abstract:      Clustering analysis provides a useful way to group objects without having previous knowledge about the data being analysed. However, the choice of clustering techniques is dependent on the structure of the dataset analysed. While research has been conducted on the general performance of clustering algorithms using arbitrary and standard datasets, in this paper, we present a case-based experiment to show the relative performance of clustering algorithms with Learning Management System log data. We compare partition-based (K-Means), density-based (DBSCAN) and hierarchical (BIRCH) methods to determine which technique is the most appropriate for performing clustering analysis within the LMS. We conclude by showing that partition-based methods produce the highest silhouette coefficient values when analysing data generated within the LMS.
   

Social Media Links

Search

Login