Discovering student models in e-learning systems

In all areas of the e-era, personalization plays an important role. Particularly in e-learning a main issue is student modeling, that is the analysis of student behavior and prediction of his/her future behavior and learning performance. In fact, nowadays, the most prevailing issue in the e-learning environment is that it is not easy to monitor students' learning behaviors. In this paper we have focused our attention on the system (the Profile Extractor) based on Machine Learning techniques, which allows for the discovery of preferences, needs and interests of users that have access to an e-learning system. The automatic generation and the discovery of the user profile, to agree as simple student model based on the learning performance and the communication preferences, allow creating a personalized education environment. Moreover, we presented an evaluation of the accuracy of the Profile Extractor system using the classical Information Retrieval metrics.