Clustering Unstructured Text Documents Using Naive Bayesian Concept and Shape Pattern Matching
Durga Toshniwal, Rishiraj Saha Roy · International Journal of Advancements in Computing Technology · 2009
Clustering organizes text in an unsupervised fashion. In this paper, we propose an algorithm for clustering unstructured text documents using naive Bayesian concept and shape-pattern matching. The Vector Space Model is used to represent our dataset as a term-weight matrix. In any natural language, semantically linked terms tend to co-occur in documents. Hence, the co-occurrences of pairs of terms in the term-weight matrix are observed. This information is used to build a term-cluster matrix where each term may belong to multiple clusters. The naive Bayesian concept is used to uniquely assign each term to a single term-cluster. The documents are assigned to clusters using mean computations. We apply shape pattern-matching to group documents within the broad clusters obtained earlier. The proposed algorithm has been validated using benchmark datasets available on the Internet. Our results show that the proposed scheme has a significantly better running time as compared to traditional algorithms.