Employing fisher discriminant analysis for Arabic text classification

Abstract Fisher's discriminant analysis; also called linear discriminant analysis (LDA), is a popular dimensionality reduction technique that is widely used for features extraction. LDA aims at finding an optimal linear transformation based on maximizing a class separability. Even though LDA shows useful results in various pattern recognition problems, such as face recognition, less attention has been devoted to employing this technique in Arabic information retrieval tasks. In particular, the sizable feature vectors in textual data enforces to implement dimensionality reduction techniques such as LDA. In this paper, we empirically investigated an LDA based method for Arabic text classification. We used a corpus that contains 2,000 documents belonging to five categories. The experimental results showed that the performance of semantic loss LDA based method was almost the same as the semantic rich singular value decomposition (SVD), and that is indication that LDA is a promising method for text mining applications.