Applying Clustering Algorithms to Solve E-learning Problems

Abstract

Several researches have been carried out in the field of the analysis of traces in a digital learning environment. The usage of e-learning platform produce large volumes of usage trace from the various actions performed by a user. However, to exploit these data, compare and improve performance, several issues are raised, to remedy this, several works that deal with this problematic are current nowadays. This research studied a series of questions about the format and the description of the data to be processed. Our goal is to share thoughts on these issues by presenting our experience in the analysis of trace-based log files, to compare several approaches used in automatic non supervised classification applied to e-learning platforms. The results and the model used is presented and discussed. Finally the encountered difficulties are presented.