University Sétif 1 FERHAT ABBAS Faculty of Sciences
Détail de l'auteur
Auteur Imad Eddine Benyahia |
Documents disponibles écrits par cet auteur
Ajouter le résultat dans votre panier Affiner la recherche
Titre : Offensive Language detection in Arabic Tweets Type de document : texte imprimé Auteurs : Imad Eddine Benyahia, Auteur ; Belaggoune Zakaria, Auteur Année de publication : 2022 Importance : 1 vol (55 f .) Format : 29cm Langues : Français (fre) Catégories : Thèses & Mémoires:Informatique Mots-clés : Schrödinger
Équation de
Équations aux dérivées partiellesIndex. décimale : 004 Informatique Résumé :
Offensive speech (vulgar or targeted offense) as an expression of heightened polarization and discourse in society has been on the rise. This is due in part to the large adoption of social media platforms that allow for greater polarization, like Facebook and Twitter. The rapid identification of offensive language in social media is of great significance for preventing viral spread and reducing the spread of malicious information.
The scope of our work lies in predicting whether the tweet post is offensive or not. We will be using the publicly available dataset from OSACT 2020 (Offensive Language Detection Dataset) for this project.
We contributed by making the training dataset balanced using the Random Under-sampling technique and different preprocessing techniques.
The experimental results on the dataset showed that the model proposed in this study can effectively extract the semantic information of offensive language and achieve state-of-the-art performance. The final comparative analysis concluded that the best model came out to be the KERAS model.Côte titre : MAI/0615 En ligne : https://drive.google.com/file/d/1WqeJMS_LcqUYoNxDdG16jDMaCcM6aCpC/view?usp=share [...] Format de la ressource électronique : Offensive Language detection in Arabic Tweets [texte imprimé] / Imad Eddine Benyahia, Auteur ; Belaggoune Zakaria, Auteur . - 2022 . - 1 vol (55 f .) ; 29cm.
Langues : Français (fre)
Catégories : Thèses & Mémoires:Informatique Mots-clés : Schrödinger
Équation de
Équations aux dérivées partiellesIndex. décimale : 004 Informatique Résumé :
Offensive speech (vulgar or targeted offense) as an expression of heightened polarization and discourse in society has been on the rise. This is due in part to the large adoption of social media platforms that allow for greater polarization, like Facebook and Twitter. The rapid identification of offensive language in social media is of great significance for preventing viral spread and reducing the spread of malicious information.
The scope of our work lies in predicting whether the tweet post is offensive or not. We will be using the publicly available dataset from OSACT 2020 (Offensive Language Detection Dataset) for this project.
We contributed by making the training dataset balanced using the Random Under-sampling technique and different preprocessing techniques.
The experimental results on the dataset showed that the model proposed in this study can effectively extract the semantic information of offensive language and achieve state-of-the-art performance. The final comparative analysis concluded that the best model came out to be the KERAS model.Côte titre : MAI/0615 En ligne : https://drive.google.com/file/d/1WqeJMS_LcqUYoNxDdG16jDMaCcM6aCpC/view?usp=share [...] Format de la ressource électronique : Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité MAI/0615 MAI/0615 Mémoire Bibliothéque des sciences Anglais Disponible
Disponible