Web Pages Clustering Using Maximum Fuzzy Spanning Tree

摘要

The amount of information on the web is growing at an exponential rate. Especially in ecommerce, Information overload on the web requires us to cluster and classify the web pages. This paper proposes algorithm that uses N-gram techniques as the tool to extract web pages' character, and presents an application of maximum fuzzy spanning tree based on fuzzy graph to the web pages clustering. This study shows that the fuzzy clustering algorithm proposed in the paper can obtain a high clustering accuracy according to web pages documents' fuzzy similarity measures.