Abstract

A recommender system is a personalized information filtering technology, used to either predict whether a target user will like a particular item (prediction problem), or to identify a set of N items that will be of interest to a certain user (top-N recommendation problem). Applying recommender systems to the field of education requires taking into account a broad set of variables that may include, among others, level of knowledge, competences, and learning styles on the part of students. Accordingly, this domain may dramatically influence both the prediction and the recommendation. Most approaches by using recommender systems are based on data explicitly collected from users to build profiles such as rankings, opinions and the like. However, in e-learning, this can be considered intrusive. This work presents the deployment and experimental evaluation of collaborative filtering algorithms on three datasets of performance history collected from students in a first-year class of a Chilean university. The aim of this paper is to analyze the impact of recommender system algorithms for educational data mining. Experimental results show that recommender systems can be a promising tool for both predicting student performance and helping students in their learning process by recommending meaningful resources.