Lightweight Document clustering Algorithm for Forum FAQ Document
Ma Lian · Microcomputer applications · 2008
Document clustering is an efficient method to organize documents,which has been widely used in unknown topic auto- mated presentation of information.The lightweight document clustering algorithm is described that operates in high dimensions, processes tens of thousands of documents and groups them into severalthousand clusters,or by varying an assigned parameter, into a few dozen clusters.Theoretic analysis and results demonstrated the algorithm could be efficient in high dimensions,both for large document collections and large numbers of clusters.