A Comparative Study of the Various Clustering Algorithms in E-Learning Systems Using Weka Tools

Clustering also called cluster analysis is the task of data objects grouping where group objects are similar. Simultaneously, they should be different from other groups objects. Such groups are termed as Clusters. We are study in this paper several clustering algorithms applied in E-learning systems. Our objective lies in performing a deep analysis of clustering data mining techniques both theoretically and experimentally and to do a comparative study in order to distinguish which technique is more suitable to identify e-learners profile and also to evaluate better student performance in engineering education. A good clustering method is able to yield high quality clusters. The algorithms under investigation are: Canopy algorithm, Cobweb algorithm, EM algorithm, FarthestFirst algorithm, FilteredClusterer algorithm, MakeDensityBasedClusterer algorithm. The performance of clustering the six algorithms is compared through the use of clustering tool WEKA (version 3.7.12) as an open source tool.

[1]  Armando Rodrigo Mor,et al.  Density-based clustering methods for unsupervised separation of partial discharge sources , 2019, International Journal of Electrical Power & Energy Systems.

[2]  Douglas H. Fisher,et al.  Knowledge Acquisition Via Incremental Conceptual Clustering , 1987, Machine Learning.

[3]  Kyle DeFreitas,et al.  COMPARATIVE PERFORMANCE ANALYSIS OF CLUSTERING TECHNIQUES IN EDUCATIONAL DATA MINING , 2015 .

[4]  Andrew McCallum,et al.  Efficient clustering of high-dimensional data sets with application to reference matching , 2000, KDD '00.

[5]  Roopali Garg,et al.  Application of Hierarchical Clustering Algorithm to Evaluate Students Performance of an Institute , 2016, 2016 Second International Conference on Computational Intelligence & Communication Technology (CICT).

[6]  Shilpa Dang,et al.  Performance Evaluation of Clustering Algorithm Using Different Datasets , 2015 .

[7]  Roshan G. Ragel,et al.  Students behavioural analysis in an online learning environment using data mining , 2014, 7th International Conference on Information and Automation for Sustainability.

[8]  Sergio Luján-Mora,et al.  Comparison of applications for educational data mining in Engineering Education , 2017, 2017 IEEE World Engineering Education Conference (EDUNINE).

[9]  Priyanka Fulare,et al.  Review of Algorithms for Clustering Random Data , 2014 .

[10]  Muhammad Ilyas,et al.  A Clustering Based Study of Classification Algorithms , 2015 .

[11]  Maria Rangoussi,et al.  Educational data mining and data analysis for optimal learning content management: Applied in moodle for undergraduate engineering studies , 2017, 2017 IEEE Global Engineering Education Conference (EDUCON).

[12]  Raoul Kwuimi,et al.  Educational Data Mining to Improve Learner Performance in Gauteng Primary Schools , 2018, 2018 International Conference on Advances in Big Data, Computing and Data Communication Systems (icABCD).

[13]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[14]  Yahya M. Tashtoush,et al.  Adaptive e-learning web-based English tutor using data mining techniques and Jackson's learning styles , 2017, 2017 8th International Conference on Information and Communication Systems (ICICS).

[15]  David B. Shmoys,et al.  A Best Possible Heuristic for the k-Center Problem , 1985, Math. Oper. Res..

[16]  Shafaatunnur Hasan,et al.  Mining of E-learning behavior using SOM clustering , 2017, 2017 6th ICT International Student Project Conference (ICT-ISPC).

[17]  T. Velmurugan,et al.  Lung Cancer Data Analysis by k-means and Farthest First Clustering Algorithms , 2015 .