Alternative Relative Discrimination Criterion Feature Ranking Technique for Text Classification

Alshalif, Sarah Abdulkarem; Senan, Norhalina; Saeed, Faisal; Ghaban, Wad; Ibrahim, Norazana; Aamir, Mohammad; Sharif, Wareesa

doi:10.1109/access.2023.3294563

Cited by 4 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Derived from the raw format available in the UCI data repository [47], this dataset is characterized by balance and comprises 20 substantial classes. The dataset encompasses a total of 20,000 messages sourced from 20 distinct newsgroups.…”

Section: Newsgroupsmentioning

confidence: 99%

Text Classification Using Deep Learning Models: A Comparative Review

Muhammad Zulqarnain,

Rubab Sheikh,

Shahid Hussain

et al. 2023

Cloud Computing and Data Science

View full text Add to dashboard Cite

With the fast popularization and continued development of web pages on the Internet, text classification has become a very serious problem in organizing and managing large amounts of digital text data in documents. The deep learning approaches have been applied in several areas of text classification with comparative and outstanding results. In this article, we analyzed and gave comprehensive reviews of the different deep learning models for text classification tasks. Based on the literature review survey, this paper addresses three various deep learning models and declares their gaps and limitations. We have evaluated the various classification applications and a small discussion on the available Deep Neural Networks (DNN) frameworks for the implementation of text datasets. The work presents guidance for future research to regulate more significance that can be distributed for the better area of this research. In summary, our study presented the main implications, identified potential directions for future research, and highlighted the challenges within this specific research field. Additionally, our aim is to acquaint readers with the various subtasks and relevant literature related to the text classification process. By engaging with our discussion, we aspire to inspire readers to explore novel and enhanced techniques for text classification, applicable across diverse domains.

show abstract

Section: Newsgroupsmentioning

confidence: 99%

Text Classification Using Deep Learning Models: A Comparative Review

Muhammad Zulqarnain,

Rubab Sheikh,

Shahid Hussain

et al. 2023

Cloud Computing and Data Science

View full text Add to dashboard Cite

show abstract

“…whereas in Embedded method, chosen model is based on incorporating the specific feature selection technique in text classification process (Bashir et al, 2022) Among three of them, the most appropriate to classify text is filter method. Selection of this method is because, it do not require any algorithm for classification of dataset (Sharif et al, 2017). RDC sort out the text, based on feature frequency, ranks high to frequent occurring terms but ignore the rare ones, which are equally important for classification of text, whereas IRDC ranks high to rare terms in text classification (Rehman et al, 2015), (Sharif et al, 2017).…”

mentioning

confidence: 99%

“…Selection of this method is because, it do not require any algorithm for classification of dataset (Sharif et al, 2017). RDC sort out the text, based on feature frequency, ranks high to frequent occurring terms but ignore the rare ones, which are equally important for classification of text, whereas IRDC ranks high to rare terms in text classification (Rehman et al, 2015), (Sharif et al, 2017). RDC and IRDC is not capable to choose effective terms for accurate classification.…”

mentioning

confidence: 99%

Enhanced Relative Discrimination Criterion and RSS-ELM Techniques to Improve the Document Classification

Anwaar,

Gilanie,

Ahmad

et al. 2024

Preprint

View full text Add to dashboard Cite

The internet is teeming with an ever-increasing amount of text information, which can come in various forms such as words, phrases, terms, patterns, concepts, sentences, paragraphs, and documents. The vast quantity of data can pose a difficulty in terms of organizing and structuring textual data effectively. In existing research work, imbalance in counting the terms hampers the classification results. We prioritize the data that precisely fits into the correct class to reduce the imbalances in the dataset and improve the overall result quality. Significant improvements are noticed in accurately classifying text by maintaining an adequate ratio of text data and using efficient text classification approaches. To improve the generalized ability of ELM, feature Selection and optimization of Deep Learning algorithms produced a great influence on classification. In this paper, the Enhanced Relative Discriminative Criterion (ERDC) and Ringed Seal Search along with Extreme Learning Machine (RSS-ELM) have been proposed for text classification. Experiments are conducted on three text datasets named: Reuter21578, 20 newsgroups, and TDT2 with a different number of classes, which shows proposed ERDC technique presents an average of 91.6% accuracy results among the previous IRDC & RDC techniques. Moreover, the proposed RSS-ELM produced a significant result of around 99.1% as compared to existing CS-ELM and GA-ELM techniques which count an average of 66%, and 54% respectively.

show abstract