Data Analysis Using Document Clustering

Abstract

Our proposed system uses clustering approach that organizes a large quantity of unstructured text documents into a small number of meaningful and coherent clusters. These measures are compared and analyzed in partitional clustering for text document datasets. Clustering provides extraction and fast retrieval of information or filtering. In document clustering, clustering methods can be used to automatically form group of the retrieved documents into a list of useful categories. Document clustering uses a sample documents as descriptors and performs descriptor retrieval from set of text documents. Descriptors is the sample document in reference to which clusters are formed.