Document Clustering Approach Using Internal Criterion Function
C. Sivasankar, D. Vivekananda Reddy · 2014
Abstract:-Document clustering is the act of collection of similar documents into bins. Fast and high quality document clustering is an important task in organizing information, search engine results obtaining results from user query, enhancing web crawling and information retrieval. With the large amount of data available and with a goal of creating good quality clusters, a variety of algorithms have been developed having quality-complexity trade offs. Among these, some algorithms seek to minimize the computational complexity using certain criterion functions which are defined for whole set of clustering solution. This paper proposes a novel document clustering algorithm based on internal criterion function. Commonly used partitioning clustering algorithms (e.g. k-means) have some drawbacks as they suffer from local optimum solutions and creation of empty clusters as a clustering solution. The proposed algorithm usually doesn’t suffer from these problems and converge to a global optimum. Further its performance enhances with the increase in the document number of clusters. The proposed algorithm has been verified against three different datasets for four different values of k (required number of clusters). Further CLUTO tool has been used to improve the performance of criterion function for document clustering.