Optimal Clustering Scheme For Repeated Bisection Partitional Algorithm

Text clustering divides a set of texts into clusters such that texts within each cluster are similar in content. It may be used to uncover the structure and content of unknown text sets as well as to give new perspectives on familiar ones. The focus of this paper is to experimentally evaluate the quality of clusters obtained using partitional clustering algorithms that employ different clustering schemes. The optimal clustering scheme that gives clusters of better quality is identified for three standard data sets. Also, the ideal clustering scheme that optimizes the I2 criterion function is experimentally identified.