A Fuzzy Similarity Based Concept Mining Model for Text Classification

TL;DR

This paper introduces a Fuzzy Similarity Based Concept Mining Model (FSCMM) for text classification that enhances accuracy by integrating fuzzy similarity analysis, feature reduction, and SVM classification across multiple corpus levels.

Contribution

The paper proposes a novel FSCMM that combines fuzzy similarity analysis with feature reduction and SVM to improve text classification accuracy and efficiency.

Findings

High accuracy results achieved in text classification

Effective feature reduction and ambiguity removal

Efficient performance across multiple corpus levels

Abstract

Text Classification is a challenging and a red hot field in the current scenario and has great importance in text categorization applications. A lot of research work has been done in this field but there is a need to categorize a collection of text documents into mutually exclusive categories by extracting the concepts or features using supervised learning paradigm and different classification algorithms. In this paper, a new Fuzzy Similarity Based Concept Mining Model (FSCMM) is proposed to classify a set of text documents into pre - defined Category Groups (CG) by providing them training and preparing on the sentence, document and integrated corpora levels along with feature reduction, ambiguity removal on each level to achieve high system performance. Fuzzy Feature Category Similarity Analyzer (FFCSA) is used to analyze each extracted feature of Integrated Corpora Feature Vector (ICFV) with the corresponding categories or classes. This model uses Support Vector Machine Classifier (SVMC) to classify correctly the training data patterns into two groups; i. e., + 1 and - 1, thereby producing accurate and correct results. The proposed model works efficiently and effectively with great performance and high - accuracy results.