Web Usage Mining Using Distributed Learning Automata

One of the most important issues in web mining is how to find out similarities between web pages. In this paper we propose a method based on distributed learning automata which take advantage of usage data to find out web pages similarities. The idea of the proposed method is that if different users request a couple of pages consistently together, then these pages are likely to correspond to the same information needs and hence can be considered similar. In the proposed method, a learning automaton is assigned to each page and is responsible for learning the similarities of that page to the other pages. It is shown that the proposed method performs better than the hebbian algorithm and the only learning automata based method reported in the literature. Furthermore, the proposed method needs lower computing time comparing to the other methods and unlike the only reported distributed learning automata based method it can be used online.