Performance of an e-learning system depends on an extent to which it is adjusted to student needs. Priorities of the last ones may differ in accordance with the context of use of an e-learning environment. For personalized e-learning system based on student groups, different distribution of the groups should be taken into account. In the paper, using of data mining techniques for building student groups depending on the context of the system use is considered. As the main technique unsupervised classification is examined,. Context parameters depending on courses and student models are tested. Experiment results for real student data are discussed.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.