A Hybrid System: Neural Network with Data Mining in an e-Learning Environment
This paper proposed a hybrid system combining the self-organizing map (SOM) of a neural network with the data mining (DM) method, for course recommendations in the e-learning system. SOM systems have been successfully used in several domains of artificial intelligence. Although many researches focused on e-learning system implementation and personal curriculum design, they do not give e-learners useful suggestions for selecting potential courses according to their interests or background. In order to enhance the efficiency and capability of e-learning systems, we combined the SOM method to deal with the cluster problems of the DM systems, SOM/DM for short. The experiment was carried out in a business college of a university in Taiwan, by applying the SOM/DM method to recommend courses to e-learners. The results indicated that the SOM/DM method has excellent performance.
KeywordsArtificial Neural Network Association Rule Mining Data Mining System Visual Basic Program Quantitative Association Rule
Unable to display preview. Download preview PDF.
- Aydin, C.H., Tasci, D.: Measuring Readiness for e-Learning: Reflections from an Emerging Country. Educational Technology & Society 8(4), 244–257 (2005)Google Scholar
- Huang, M.J., Chen, M.Y., Lee, S.C.: Integrating Data Mining with Case-based Reasoning for Chronic Diseases Prognosis and Diagnosis. accepted to appear in Expert Systems with Applications 32(3), 856–867 (2007)Google Scholar
- International Data Corporation Website, http://www.idc.com/
- Ma, Z.: Web-Based Intelligent e-Learning Systems: Technologies and Applications, Information Science Publishing, pages 388 (2006)Google Scholar
- Rashid, A.M., Albert, I., Cosley, D., Lam, S.K., McNee, S., Konstan, J.A.: Getting to know you: Learning new user preferences in recommender systems. In: Proceedings of the 2002 international conference on intelligent user interfaces, pp. 127–134 (2002)Google Scholar