An Efficient Productive Feature Selection and Document Clustering (PFS-DocC) Model for Document Clustering

In mining, document clustering pretends to diminish the size by constructing model which is extremely essential in various web-based applications. Over past few decades, mining approaches are analysed and evaluated enhance process of attain better results; however, most cases, documents messed up degrade performance reducing level accuracy. The data instances need be organized a productive summary have generated for all clusters. or description should demonstrate information users’ devoid any further analysis helps easier scanning associated It performed identifying relevant influencing features generate cluster. This work provides novel approach known as Productive Feature Selection Document Clustering (PFS-DocC) model. Initially, selected from input dataset DUC2004 benchmark dataset. Next, attempted single multiple clusters where output has more extractive, generic, appropriate suitable summaries well-suited experimentation carried out online available evaluation shows that proposed PFS-DocC gives superior outcomes with higher ROUGE score.