Document Clustering Using Gravitational Ensemble Clustering

Text Mining is a field that is considered as an extension of data mining. In the context of text mining, document clustering is used to set apart likewise documents of a collection into the identical category, called cluster, and divergent documents to distinctive groups. Since every dataset has its own characteristics, finding an appropriate clustering algorithm that can manage all kinds of clusters, is a big challenge. Clustering algorithms has theirs unique approaches for computing the number of clusters, imposing a structure on the data, and attesting the out coming clusters. The idea of combining different clustering is an effort to overwhelm the faults of single algorithms and further enhance their executions. On the other hand, inspired by the gravitational law, different clustering algorithms have been introduced that each one attempted to cluster complex datasets. Gravitational Ensemble Clustering (GEC) is an ensemble method that employs both the concepts of gravitational clustering and ensemble clustering to reach a better clustering result. This paper represents an application of GEC to the problem of document clustering. The proposed method uses a modification of the original GEC algorithm. This modification tries to produce a more varied clustering ensemble using new parameter setting. The GEC algorithm is assessed using document datasets. Promising results of the presented method were obtained in comparison with competing algorithms.