University Sétif 1 FERHAT ABBAS Faculty of Sciences
Détail de l'auteur
Auteur Akram Djidel |
Documents disponibles écrits par cet auteur
Ajouter le résultat dans votre panier Affiner la recherche
Titre : Deep Learning Based Sentiment Analysis of Movie Reviews Type de document : texte imprimé Auteurs : Akram Djidel, Auteur ; Islam Djemmal, Auteur ; Allaoua Refoufi, Directeur de thèse Année de publication : 2022 Importance : 1 vol (77 f .) Format : 29cm Langues : Français (fre) Catégories : Thèses & Mémoires:Informatique Mots-clés : Informatique Index. décimale : 004 Informatique Résumé : As a result of the advent of social media, there is a huge quantity of data and opinions that are exchanged. For building opinion mining systems, sentiment analysis has become important. It uses reviews and tweets to try to know how people feel about a certain product, film, or issue. In the field of sentiment analysis, several previous research using various neural network architectures have been published. In this work study, we used the Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) model to solve the sentiment analysis of movie reviews problem in Natural Language Processing (NLP). This model was applied on the IMDB dataset consisting of 140K movie reviews. The data was initially pre-processed and word embedding was applied accordingly. Our results show that this proposed model can achieve a very high performance compared to other models with an overall accuracy greater than 96%. . Côte titre : MAI/0603 En ligne : https://drive.google.com/file/d/1OJOIKxf5w2nIJ1D00skiFdxBt3qpp5dU/view?usp=share [...] Format de la ressource électronique : Deep Learning Based Sentiment Analysis of Movie Reviews [texte imprimé] / Akram Djidel, Auteur ; Islam Djemmal, Auteur ; Allaoua Refoufi, Directeur de thèse . - 2022 . - 1 vol (77 f .) ; 29cm.
Langues : Français (fre)
Catégories : Thèses & Mémoires:Informatique Mots-clés : Informatique Index. décimale : 004 Informatique Résumé : As a result of the advent of social media, there is a huge quantity of data and opinions that are exchanged. For building opinion mining systems, sentiment analysis has become important. It uses reviews and tweets to try to know how people feel about a certain product, film, or issue. In the field of sentiment analysis, several previous research using various neural network architectures have been published. In this work study, we used the Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) model to solve the sentiment analysis of movie reviews problem in Natural Language Processing (NLP). This model was applied on the IMDB dataset consisting of 140K movie reviews. The data was initially pre-processed and word embedding was applied accordingly. Our results show that this proposed model can achieve a very high performance compared to other models with an overall accuracy greater than 96%. . Côte titre : MAI/0603 En ligne : https://drive.google.com/file/d/1OJOIKxf5w2nIJ1D00skiFdxBt3qpp5dU/view?usp=share [...] Format de la ressource électronique : Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité MAI/0603 MAI/0603 Mémoire Bibliothéque des sciences Anglais Disponible
Disponible