Web Snippets Clustering Based on an Improved Suffix Tree Algorithm

Web search results clustering is the navigator for users to find relevant results quickly. Through combining the advantages of vector space model (VSM) and suffix tree clustering (STC) document models, this paper puts forward a more effective Web snippets clustering algorithm. It can take into account the semantic information of candidate label phrases, and offer descriptive, readable and conceptual topic labels for the final documents groups. Evaluation of results demonstrates that clustering Web snippets based on the improved suffix tree algorithm has better performance in making search engine results easy to browse and helping users quickly find Web pages that they are interested in.