Alternative Relative Discrimination Criterion Feature Ranking Technique for Text Classification
Alshalif, Sarah Abdulkarem and Senan, Norhalina and Saeed, Faisal and Ghaban, Wad and Ibrahim, Noraini and Aamir, Muhammad and Sharif, Wareesa (2023) Alternative Relative Discrimination Criterion Feature Ranking Technique for Text Classification. IEEE Access. p. 1. ISSN 2169-3536
|
Text
Alternative_Relative_Discrimination_Criterion_Feature_Ranking_Technique_for_Text_Classification.pdf - Published Version Available under License Creative Commons Attribution. Download (824kB) |
Abstract
The use of text data with high dimensionality affects classifier performance. Therefore, efficient feature selection (FS) is necessary to reduce dimensionality. In text classification challenges, FS algorithms based on a ranking approach are employed to improve the classification performance. To rank terms, most feature ranking algorithms, such as the Relative Discrimination Criterion (RDC) and Improved Relative Discrimination Criterion (IRDC), use document frequency (DF) and term frequency (TF). TF accepts the actual values of a term with frequently and rarely occurring terms used in existing feature ranking algorithms. However, these algorithms focus on the number of terms in a document rather than the number of terms in the category. In this research, an alternative method to RDC, called Alternative Relative Discrimination Criterion (ARDC) was proposed, which aims to improve the accuracy and effectiveness of RDC feature ranking. Specifically, ARDC is designed to identify terms commonly occurring in the positive class. The results obtained were compared to the existing RDC methods, which are RDC and IRDC, and standard benchmarking functions such as Information Gain (IG), Pearson Correlation Coefficient (PCC), and ReliefF. The experimental results reveal that using the suggested ARDC on the Reuters21578, 20newsgroup, and TDT2 datasets provides better performance in terms of precision, recall, f-measure, and accuracy when employing well-known classifiers such as multinomial naïve Bayes (MNB), Support Vector Machine (SVM), Multilayer perceptron (MLP), k-nearest neighbor (KNN), and decision tree (DT). Another experiment was performed to validate the proposed technique, which aims to showcase the novelty of the ARDC approach. The experiment utilized the 20newsgroup dataset and employed the Relevant-Based Feature Ranking (RBFR) technique. Naïve Bayes (NB), Random Forest (RF) and Logistic Regression (LR) classifiers were used in this experiment to demonstrate the effectiveness of the suggested ARDC.
| Item Type: | Article | ||||||
|---|---|---|---|---|---|---|---|
| Identification Number: | https://doi.org/10.1109/ACCESS.2023.3294563 | ||||||
| Dates: |
|
||||||
| Uncontrolled Keywords: | Text categorization, Feature extraction, Classification algorithms, Measurement, Support vector machines, Filtering algorithms , Accuracy | ||||||
| Subjects: | CAH11 - computing > CAH11-01 - computing > CAH11-01-01 - computer science | ||||||
| Divisions: | Faculty of Computing, Engineering and the Built Environment > School of Computing and Digital Technology | ||||||
| Depositing User: | Gemma Tonks | ||||||
| Date Deposited: | 18 Jul 2023 09:52 | ||||||
| Last Modified: | 18 Jul 2023 09:52 | ||||||
| URI: | https://www.open-access.bcu.ac.uk/id/eprint/14612 |
Actions (login required)
 |
View Item |
Tools
Tools