Improved Suffix Tree Clustering for Efficient Document Clustering

Abstract

Document clustering is a technology that puts pages into groups and is useful for categorizing, organizing, and refining search results.
When clustering using only documents, Suffix Tree Clustering (STC) outperforms other clustering algorithms by making use of phrases and
allowing clusters to overlap. STC is a linear time clustering which is based on identifying phrases that are common to groups of documents. STC
treats a document as a string, making use of proximity information between words, at the same time, it is incremental. Suffix Tree Clustering has
been proved to be a good approach for documents clustering. This paper introduces the suffix tree based document clustering with cluster
ranking function and a new ranked list of clusters after applying in the algorithm is introduced to overcome the problems with overlapping
clusters. Using this method, we can get a better clustering result and effective number of clusters.

Keywords: Suffix Tree; Document Clustering; STC; Web Document; Ranked cluster.