PRAGMATIC APPROACH FOR DIGITAL DATA CLUSTERING USING I-DELEGATE ALGORITHM

Now a day, we use all new scientific and technical process in digital world to create huge digital documents so, the analysis of such huge set of document is really difficult and more important work. Document clustering should be an automatic process where documents are partition into clusters having high likeness based on input term. It is a popularly studied problem in text classification but generally the study of analogy measure for document clustering is not based on keywords normally domain based clustering is done. Our main aim is to improve the accessibility, scalability and usability of text mining for various applications. So, to do text document analysis within a stipulated time is a key factor. So it’s not an easy work for examiner to do such analysis in quick period of time. That’s why to do the digital document analysis within less period of time, requires particular techniques to make such difficult task in a simpler way. Such special technique called document clustering. So, clustering algorithms are of great advantage. Here we proposed a I-Delegate algorithm which uses Jaccard distance measure for computing the most dissimilar k documents as centroids for k clusters. Our pragmatic experimental results display that our implemented I-delegate algorithm with Jaccard distance measure for computing the centroid improves the clustering performance of the simple K-means algorithm. The accuracy of clustering of documents has been improved by means of this I-delegate approach due to synonym identification and delegates that synonym to clustering process along with near index approach for better result. Keywords— Documents clustering; I-delegate Algorithm; Jaccard similarity coefficient; K-Means Algorithm