Clustering the Navigation Pattern Using Graph Partitioning

Abstract

World Wide Web become as information gateway and as a medium for conducting business. People use web pages to retrieve information which may need or demand. Web mining can provide the navigation link to user by using user behavior. This system provides clustering of user navigation patterns based on graph partitioning algorithm. For clustering of user navigation patterns, the system creates an undirected graph based on connectivity between each pair of web pages and assigns weight to edges in such graph. Those weights are then used in clustering algorithm based on graph partitioning. These system results can be used to improve the overall performance of future access and the clusters concerning user navigation pattern can be used for web caching.