Skip to Main Content
Based on Discovery Feature Sub-space Model (DFSSM), this paper proposes a new web text clustering algorithm which characterizes self-stability and powerful antinoise ability. The definitions of cluster and distance measures in the concept space being given. It can distinguishes the most meaningful features from the Concept Space without the evaluation function. The application in the modern long-distance education system prove it is efficient and effective. Through the analysis of results, this algorithm has better performance than traditional approaches.