Analysis of Different Clustering Techniques in Data and Text Mining
S. Krishna Prabha, K. S. Rangasamy, K. Duraiswamy, K. S. Rangasamy Dean, Muthusethupathi Sharmila · 2014
In recent days clustering becomes important in pattern detection, unsupervised learning process, data concept construction, information retrieval, text mining, web analysis, marketing and medical diagnostic. The purpose of this paper is an attempt to reconnoiter some of the important clustering techniques in the data mining literature and to compare some aspects of clustering algorithms which contains performance, order of input, accuracy, scalability, shapes discovered, dimensionality and dealing with noisy data. The algorithms are Partitional approach, hierarchical approach, seeded approach, ontology approach, concept based approach.