An enhanced fuzzy similarity based concept mining model for text classification using feature clustering

In the current era, the feature reduction is an essential part of the classification algorithms, methodologies and algorithms. When a set of features is extracted from a text document, then these features collectively make a huge, large volume high dimensional data set and contain large space and long time to be processed each time. This challenge requires a new text classification forum which can find the solution to remedy it. In this paper, a Fuzzy Similarity based Concept Mining Model Using Feature Clustering (FSCMM-FC) is proposed which capably categorizes various seen and known text documents into different predefined and mutually exclusive categories groups by keeping the data (or feature set dimension) very low. The paper also discusses a case study of 4 text documents to analyze the proposed system. The analysis shows that the system provides 70-75% improved results; thereby increasing the system performance drastically.