Revue de l'Information Scientifique et Technique
Volume 27, Numéro 2, Pages 1-6
2023-11-08

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



Authors : Barmati Mohammed Elsadiq . Bachir Said .

Abstract

With the emergence of Pre-trained Language Models (PLMs) and the success of large scale, the field of Natural Language Processing (NLP) has achieved tremendous development such as Sentiment analysis (SA) that is one of the fast-growing research tasks in NLP. This paper describes the system that our team submitted to the CERIST NLP Challenge 2022 for task1.b. The purpose of this task is to identify the sentiment polarity of the CERIST NLP Challenge 2022 datasets in English and Arabic languages comments collected from twitter. Our approach is based on a PL Model called XLM-T, and uses the Oversampling technique to solve the sentiment analysis problem of multilingual in twitter. Experimental results confirm that this state-of-the-art model is robust achieving accuracy of 85%.

Keywords

Natural Language Processing ; Sentiment analysis ; Pre-trained Language Model ; CERIST NLP Challenge 2022 task1.b ; XLM-T ; Oversampling technique

Les articles similaires

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

Said Bachir .  Barmati Mohammed Elsadiq . 
pages 13-17.

Sentiment Analysis Using R: Applied Study Of The Mobile Phone Market

Balouli Houssame Eddine .  Chine Lazhar . 
pages 447-461.

Modeling Sentiment Analysis Using Machine Learning Algorithms For Arabic Covid-19 Tweets

Elhakeem Yousra F.g .  Eltayeb Safa .  Aldawsari Mohammed .  Salih Dawood Omer Omer . 
pages 29-35.

Les Hashtags Sur Twitter Du Technique à L'expressif : Regard Sur Les Pratiques Discursives

Medane Hadjira . 
pages 348-357.

Xml_gfd : Un Générateur Dynamique De Formulaires Xlm Valides Dtd

Maredj Azze-eddine .  Khouatmi-boukhatem Samia .  Adjerad Halima Douniazed . 
pages 1-13.

Formats de citation