Grid-enabled Support for Classification and Clustering of Textual Documents

This paper presents the fusion of two approaches – Grid and Grid computing and text mining. GridMiner is a system developed at University of Vienna, and it is a framework for knowledge discovery process in the distributed Grid environment. JBOWL is a framework for text mining and information retrieval being developed at Technical University in Košice. Text mining provides some methods (including the classification and clustering) in order to automatically extract the relevant knowledge contained in the textual documents. The inclusion of the Grid text mining services into the Grid-based knowledge discovery system can support problem solving process on such a system. Motivation of the presented work is to use the Grid computational capabilities for text mining tasks and text classification or clustering in particular.