A new method of class centriod vectors classification based on the feedback

It is a great challenge for information technology that how to organize and manage large amount of document data, and find users' interested information quickly and exactly. Text classification can achieve the goal of information distributaries and solve the problem of information disorder, and then it can offer the convenience to users to make decisions. Centroid classifier is one of the most efficient models. Firstly the paper expatiates on the disadvantage of traditional weight calculation method applied in text classification, and then a new method which uses feature selection evaluation function value as a factor to term frequency is proposed. This paper present an improved centroid classifier based on feedback. The main idea of the algorithm is using the misfit samples in the training set to modify the center vectors which are related with them. From test results, the algorithm proposed by the paper is valid.