University Sétif 1 FERHAT ABBAS Faculty of Sciences
Détail de l'auteur
Auteur Aicha Guerras |
Documents disponibles écrits par cet auteur
Ajouter le résultat dans votre panier Affiner la recherche
Titre : Event detection in Twitter Type de document : texte imprimé Auteurs : Aicha Guerras, Auteur ; Sefiane Rayhana, Auteur ; Abdelaziz Lakhfif, Directeur de thèse Année de publication : 2022 Importance : 1 vol (78 f .) Format : 29cm Langues : Français (fre) Catégories : Thèses & Mémoires:Informatique Mots-clés : Event detection Index. décimale : 004 Informatique Résumé :
In recent years, event detection task has become an interesting area of research
in the natural language processing community. event detection is
the process of analyzing event flows in order to identifying the event trigger
and classifying it under one of the predefined events types. Therefore, in
this thesis we propose an approach to detect events and use twitter as a
source of our data.
The first phase from our approach was extract tweets form twitter using
REST API, we choose a group of users utilize Modern standard Arabic language
to complete this phase. Then, we applied preprocessing phases such
as cleaning, normalization. after that we applied a set of feature extraction
techniques, TF-IDF and word embedding in preparation for implementing
the classical classifiers and deep learning. The results that we obtained
show the accuracy of our approach.Côte titre : MAI/0610 En ligne : https://drive.google.com/file/d/1n9YWyLxK7dPxZhaLFOub72xKpWZ9NXHs/view?usp=share [...] Format de la ressource électronique : Event detection in Twitter [texte imprimé] / Aicha Guerras, Auteur ; Sefiane Rayhana, Auteur ; Abdelaziz Lakhfif, Directeur de thèse . - 2022 . - 1 vol (78 f .) ; 29cm.
Langues : Français (fre)
Catégories : Thèses & Mémoires:Informatique Mots-clés : Event detection Index. décimale : 004 Informatique Résumé :
In recent years, event detection task has become an interesting area of research
in the natural language processing community. event detection is
the process of analyzing event flows in order to identifying the event trigger
and classifying it under one of the predefined events types. Therefore, in
this thesis we propose an approach to detect events and use twitter as a
source of our data.
The first phase from our approach was extract tweets form twitter using
REST API, we choose a group of users utilize Modern standard Arabic language
to complete this phase. Then, we applied preprocessing phases such
as cleaning, normalization. after that we applied a set of feature extraction
techniques, TF-IDF and word embedding in preparation for implementing
the classical classifiers and deep learning. The results that we obtained
show the accuracy of our approach.Côte titre : MAI/0610 En ligne : https://drive.google.com/file/d/1n9YWyLxK7dPxZhaLFOub72xKpWZ9NXHs/view?usp=share [...] Format de la ressource électronique : Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité MAI/0610 MAI/0610 Mémoire Bibliothéque des sciences Anglais Disponible
Disponible