A COPRAS-based Approach to Multi-Label Feature Selection for Text Classification

Abstract

In this article, we present a novel approach for text classification feature selection using a pseudo-relation matrix constructed with ridge regression. This approach involves generating a matrix that captures the relationship between features and target variables and then using that matrix to create a multi-criteria decision making (MCDM) problem. We then utilize the Complex Proportional Assessment (COPRAS) method to rank features in order of importance. To assess the performance of our proposed algorithm, we conduct tests on ten real-world text datasets and compare our results to the existing methods. Our findings indicate that the proposed approach outperforms other methods, and we provide statistical significance to support our claims. Our proposed algorithm provides a viable answer for researchers looking for efficient and effective feature selection methods for text data analysis, which can lead to a better understanding and interpretation of the underlying text.