عنوان مقاله [English]
In this paper, we firstly review some definitions related to fractional calculus and fractional entropy, as a generalization of Shannon entropy. Then we introduce the generalized word importance metric based on fractional entropy. Using the proposed definition, we introduce a new text mining method based on fractional entropy. This method for keyword extraction of the Statistical Inference book by Casella and Berger (1990) shows that the F-measure value of the proposed text mining method, is higher than the related value for common text mining method based on Shannon entropy. These results indicate that the proposed text mining method based on fractional entropy is more comprehensive than the traditional text mining based on Shannon entropy.