Identifying the user typology for adaptive e-learning systems

Adaptive e-learning systems are the newest paradigm in modern learning approaches. One of the key factors in such systems is the correct and continuous identification of the user learning style, such as to provide the most appropriate content presentation to each individual user. This paper presents a new possibility for identifying the initial user typology, based on static features, in an adaptive e-learning system previously designed by our team. We propose the employment of a clustering method to determine the different groups of learning typologies, corresponding to the theoretical learning styles present in literature. The evaluation results suggest that clustering provides a better correspondence between the individuals and the learning styles than a previous classification performed with Bayesian networks. Moreover, the discrepancies observed in the results can be eliminated by careful design of the psychological test which measures the initial user static features.