Web Co-clustering of Usage Network Using Tensor Decomposition

Web clustering is an approach to aggregate web objects into various categories according to underlying relationships among them. Finding co-clusters of web objects is an emerging topic in the context of web usage mining. In this paper we will present an algorithm using tensor decomposition to co-cluster web objects based on analysis of user navigational tasks. The usage data of users visiting web sites is collected as experimental data to construct the usage network and validate the presented method. Experimental results have demonstrated the proposed method can clearly reveal the aggregations of web objects as a result of different navigational tasks.