Fuzzy Clustering and Visualization of Information for Web Search Results

Searching for information on the web is a common task. Often information on the web is distributed, semi-structured, overlapping and heterogeneous. Organization and Visualization of this information is an active area of research where the goal is to help users locate required information in web pages efficiently. The most widely used data organization technique is clustering. This paper introduces a new clustering algorithm to organize web pages, and a visualization method which facilitates users to search information efficiently from the web. The algorithm presented is a hierarchical fuzzy clustering algorithm which uses domain knowledge to determine input parameters as opposed to other existing algorithms in the literature. The comparative results show that the algorithm performs as well as existing algorithms. Next, we present a methodology to visualize the clustered collection of documents and their contents such that users can visually explore data and extract information. A detailed example is presented to demonstrate various views to visualize clusters, documents and the keywords present in the web pages.