Revue de l'Information Scientifique et Technique
Volume 27, Numéro 2, Pages 13-17
2023-11-08

Cerist Nlp-challenge2022: Gigabert-based Approach For Hate Speech Detection In Arabic Twitter



Authors : Said Bachir . Barmati Mohammed Elsadiq .

Abstract

Natural Language Processing has recently become one of the most trending research areas in Artificial Intelligence, especially in social media-related tasks. This paper describes our participation in the "Hate Speech Detection on Arabic Twitter” task at the CERIST NLP-Challenge 2022 competition. The proposed solution aims to classify the tweets collected in the Arabic ARACOVID19-MFH multi-label and multi-dialect dataset into "Hateful" and "Not Hateful" categories. Based on a pre-trained transformer model known as GigaBERT-v4, our solution outperformed the most common transformer models supporting the Arabic language. Experiments have proved that the GigaBERT-v4 model is more effective than the other models using the previously described dataset, obtaining a 99.46% accuracy and a 98.68% macro F1-score.

Keywords

Arabic Twitter ; hate speech detection ; multilingual transformers ; GigaBERT-v4 ; XLM-T ; AraBERT ; mBERT ; COVID'19

Les articles similaires

Cerist Nlp-challenge2022: Xlm-t For Multilingual Sentiment Analysis In Twitter Using Oversampling Technique

Barmati Mohammed Elsadiq .  Bachir Said . 
pages 1-6.

Hate Speech Detection Model Based On Bert For The Arabic Dialects

Chiker Nour Elhouda . 
pages 36-43.

Transformers And Ensemble Methods: A Solution For Hate Speech Detection In Arabic Language

Magnossão De Paula Angel Felipe .  Bensalem Imene .  Rosso Paolo .  Zaghouani Wajdi . 
pages 7-12.

A Logistic Regression Algorithm For Arabic Hate Speech Detection

Sellidj Abdelmounim . 
pages 44-49.

Arabic Hate Speech And Social Networks Offensive Language Detection

Bouchal Hakim .  Belaid Ahror . 
pages 24-28.

Formats de citation