A Transformer-Based Model for Sentiment Analysis on Big Data Platforms

Q: How can I download an article?

To download an article from SID, first log in to the site, search for the article title, and click on the 'Download Article' option.

Q: How can I download an ISI article?

To download an ISI article on SID, enter the keyword or article title in the search bar, view the relevant results, click on the desired article, and select the 'Download Article' option.

Q: How can I access the SID database?

To access the SID database, visit SID.ir, create an account, and log in to access scientific resources.

Q: Is downloading articles from SID free?

Some articles on SID are available for free, while others require payment. Details are specified on the article's page.

Noroozi Mohammad Reza; Moeini Ali

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

Journal Paper

Paper Information

Journal: ACCOUNTING, FINANCE AND COMPUTATIONAL INTELLIGENCE Year:2024 | Volume:2 | Issue:3 Page(s): 33-44

Download Full-Text

Persian Verion

View:

Download:

Cites:

Information Journal Paper

Title

A Transformer-Based Model for Sentiment Analysis on Big Data Platforms

Author(s)

Noroozi Mohammad Reza | Moeini Ali | Issue Writer Certificate

Keywords

CNN

RCNN

Sentiment analysis

big data

adversarial learning

ParserBert

FaberBert

multilingual BERT

Abstract

This study addresses the challenges of sentiment classification arising from the vastness of textual data by introducing a three-phase adversarial fine-tuning framework. In this framework, a base model is trained using a transformer encoder, multi-head attention, and a BiLSTM layer on preprocessed data, followed by the creation of a systematic generator that applies fourteen controlled perturbations at varying intensities to the adversarial datasets. In the base article, stage-wise training was conducted sequentially on preprocessed data and on different levels of adversarial datasets, demonstrating significant improvements particularly on a noisy dataset (level 3). Overall, this approach effectively enhances the robustness and reliability of sentiment classifiers in big data contexts with corrupted text. In the proposed method, by incorporating an optimized RCCN network and multi-agent SVM-based clustering, factors were re-clustered, resulting in the proposed algorithm achieving an accuracy rate of 97.86%.

Multimedia

No record.

Cites

No record.

References

No record.

Cite

Related Journal Papers

No record.

Related Seminar Papers

No record.

Related Plans