Resumen de Detecting atypical student behaviour on a e-learning system
Félix Castro, Alfredo Vellido Alacena 
, Angela Nebot Castells , Julià Minguillón
E-learning systems such as virtual campus environments have established themselves as a strong alternative to traditional distance university education. In this scenario, the Internet allows the gathering of information on many aspects of students’ online behavior in nearly real time. The knowledge extracted from this information can be used to define personalization strategies tailored to the students’ needs and requirements. In this brief study we introduce a model to detect atypical behavior on the grouping structure of the users of a real virtual campus (Open University of Catalonia). Experiments carried out on these data indicate that atypical students’ behavior can be identified and interpreted with a novel model that, simultaneously, neutralizes the negative impact of outliers on the data clustering process.
