Learner’s Dropout Analytics Using Modern Coherent Rule Optimization Technique

Author(s) : M.Ravichandran , DrG.Kulanthaivel , Dr.T. Chellatamilan

Volume & Issue : VOLUME 1 / 2016 , ISSUE 1

Page(s) : 44-50


Abstract

The rate of increase of dropout learner in e-learning environment is quite high in recent years. The reason for the dropout is also countless. Hence it is required to formulate the system for analyzing the learners profile in e-learning. Educational Data Mining system is mainly focused for analyzing and improving the efficacy of teaching learning process. In this research, we propose a novel method for identifying the reasons for dropout of online learners from the Moodle platform using modern machine learning and association rule mining techniques .The rules generated for discovering the new pattern of dropouts are optimized using modern coherent rule optimization(MCRO).The results are visualized with dropout pattern comparison. This analysis helps the facilitators for customizing the learning platform and to reduce the number of dropout learners.



Keywords

e-learning, Dropout learner, Association rule optimization, Educational data mining.

References

[1]. Nawal Sael1, Abdelaziz Marzak2 and Hicham
Behja3, Multilevel clustering and association rule
mining for learners’ profiles analysis. IJCSI
International Journal of Computer Science Issues,
Vol. 10, Issue 3, No 1, May 2013ISSN (Print): 1694-
0814 | ISSN (Online): 1694-0784
[2]. Enrique García1, Cristóbal Romero1, Sebastián
Ventura1, Toon Calders2, Drawbacks and solutions
of applying association rule mining in learning
management systems, Workshop on Data Mining for
User Modeling at UM’07 (2007) 81-90.Proceedings
of the International Workshop on Applying Data
Mining in e-Learning 2007
[3] R. Cooley, B. Mobasher, and J. Srivastava. Web
mining:information and pattern discovery on the
world wide web. In9th IEEE International
Conference on Tools with ArtificialIntelligence,
pages 558–567, 1997.
[4].Khribi, M. K., Jemni, M., &Nasraoui, O. (2009).
Automatic Recommendations for E-Learning
Personalization Based on WebUsage Mining
Techniques and Information Retrieval. Educational
Technology & Society, 12 (4), 30–42.
[5].Shahabi, C., Zarkesh, A. M., Adibi, J., & Shah,
V. (1997). Knowledge Discovery from User’s Webpage
Navigation.Paperpresented at the 7th IEEE
International Conference on Research Issues in Data
Engineering, April 7-8, Birmingham, UK.
[6].A.AnithaDr.N.Krishnan, A Dynamic Web
Mining Framework for ELearningRecommendations
using Rough Sets and
AssociationRuleMining,International Journal of
Computer Applications (0975 – 8887)Volume 12–
No.11, January 2011
[7].
ZailaniAbdullah,TututHerawan,NoraziahAhmad,Mu
stafa Mat deris, “Extracting highly positive
association rules from students’ enrollment
data”,Procedia - Social and Behavioral
SciencesVolume 28, 2011, Pages 107–111.
[8]KunyanuthKularbphettong,Phanuwaraporn,Cholti
chatongsiri,”Analysis of student motivation behavior
on e-learning based on association rule
mining”,International journal of
computer,electrical,Automation,control and
information engineering,vol(6).No 6.2012.