NMF-based method of text classification

This paper put forward a text classification method based oil NIYIF (Non-negative -Matrix Factorization), NMF-based analysis of the conceptual semantic space and the text rector dimensionality reduction- better explain the concept of the semantic vector, better reflect the local features of the text, comparison of two methods of generating conceptual semantic space based on NMF and SVD (Singular Value Decomposition). Experimental results show that the local conceptual semantic space generated based on NMF can be a better text classification accuracy.