Abstract: On the Internet, the illegal copying and piracy of text arc becoming increasingly serious, so there is an urgent need for effective text copyright protection method. This paper proposed a new text copyright protection method based on text feature extraction and text classification techniques. The experiments show that the proposed algorithm can distinguish the different authors and can effectively classify a controversial literary works, and identify the real author.Therefore the method can assist to resolve the copyright disputes of dispute works (especially the famous works) to mamtam mtcgnty.

Key words: Feature extraction, Data mining, Copyright protection