User centric dynamic web information visualization

Visualization of information after retrieval from the World Wide Web is a very challenging task because of the huge amount of data in cyberspace. Based on rules, information is retrieved through mining techniques and then visualized in different ways. The web-graph is one way for users to visualize web data and its connectivity. But because of its huge size, the web-graph lacks simplicity for end users. Though clustering plays a very important role in reducing the complexity of the web graph by making it compact and simple, existing clustering techniques are insufficient to provide personalized visualization for users. Hence, these clustering techniques end up showing the same clustered graph to every user, despite their varying interests. This work aims to make information visualization personalized based on user interests; to provide a good first impression of web information to end users; to make web navigation easier; and to create scope for further analysis. Specifically, we develop a system for clustering which first considers user interests and then visualizes the clustered web graph to make the information more useful to the end users. In this paper, we present some experimental examples that show the improvements achieved by our approach over existing ones.