Effective e‐learning recommendation system based on self‐organizing maps and association mining

Abstract

Purpose: The purpose of this study is to propose a hybrid system to combine the self‐organizing map (SOM) of a neural network with the data‐mining (DM) method for course recommendation of the e‐learning system. Design/methodology/approach: This research constructs a hybrid system with artificial neural network (ANN) and data‐mining (DM) techniques. First, ANN is used to classify the e‐Learner types. Based on these e‐Learner groups, users can obtain course recommendation from the group's opinions. When groups of related interests have been established, the DM will be used to elicit the rules of the best learning path. It is ideal for this system to stimulate learners' motivation and interest. Moreover, the hybrid approach can be used as a reference when learners are choosing between classes. Findings: In order to enhance the efficiency and capability of e‐learning systems, the SOM method is combined to deal with cluster problems of DM systems, SOM/DM for short. It was found that the SOM/DM method has excellent performance. Research limitations/implications: This research is limited by the fact that its participants are from a business college of a university in Taiwan, and it is applied by SOM/DM to recommend courses of e‐learners. This research is useful in the domain of the e‐learning system. Originality/value: The results of this research will provide useful information for educators to classify their e‐learners or students more accurately, and to adapt their teaching strategies accordingly to retain valuable e‐learners subject to limited resources. The experiments prove that it is ideal to stimulate learners' motivation and interest.