Building an e-learning recommender system using Association Rules techniques and R environment

By Karim Dahdouh, Lahcen Oughdir, Ahmed Dakkak, Abdelali Ibriz

Abstract


To help the human mind in its process of selecting and filtering information, several recommendation systems have been developed in multiple application domains, such as e-commerce and e-tourism. Recommender systems are built to guide end users to easily find the most proper items on huge amount of data. In other words, this type of system tries to suggest items that best meet the preferences and needs of a user. It can be represented as a unit for predicting the behavior of a user by anticipating his next actions.

In this article, we develop a courses recommender system dedicated to online learning environment. It aims to discover relationships between student’s courses activities using association rules method in order to help the student to choose the more appropriate learning materials. We also focus on the analysis of past historical data of the courses enrollments or log data. The article discusses particularly the frequent itemsets concept to determine the interesting rules in the transaction database. Then, we use the extracted rules to find the catalog of more suitable courses according to the learner’s behaviors and preferences. Next, we implement our system using the FP-growth algorithm and R programming language. Finally, the experimental results prove the effectiveness and reliability of the proposed system to increase the quality of student’s decision and orientate them during the learning process by providing most relevant pedagogical resources.

Full Text:

PDF