Frequent Concepts-based Document Clustering using Correlation (FCDCC)

Document clustering (text clustering) is the way by which meaningful patterns can be extracted from large datasets.It helps to achieve prompt information retrieval, precise topic mining or in short streaming.Document clustering is useful in the extent of filtering out similar documents and further finding the distinct topics and subtopics.Huge amount of information is available as documents on online sources such as Newswire and different Blogs.Document clustering techniques can be used for managing such document datasets.But high dimensionality is still a big challenge for mostly Document clustering algorithms.In this paper a new and efficient methodology of document clustering using correlation analysis is presented to address the problem of high dimensionality and finding a better solution.