Belief Rough Set Classification for web mining based on dynamic core

In this paper, we apply classification system denoted Belief Rough Set Classifier (BRSC) based on the hybridization of belief functions and rough sets to learn decision rules from uncertain data consisting of web usage. The uncertainty appears only in decision attributes and is handled by the Transferable Belief Model (TBM), one interpretation of the belief function theory. The web usage mining dataset was obtained from an educational website, where the visits were clustered based on study patterns. Instead of using crisp assignment of a visit to one of the clusters, the study associated a belief that the visit will belong to that cluster. Due to the uncertainty existing in the chosen web usage mining database, the feature selection step used to construct our BRSC will be based on dynamic core approach which allows getting better performance in uncertain and large database. To judge the performance of our classifier, we choose three evaluation criteria: accuracy, size and time requirement. Besides, we compare the results with those obtained from a similar classifier, namely Belief Decision Tree (BDT).