Analysis of implicit opinions in social networks / Arrar ,Djihad  

Public ISBD Titre : Analysis of implicit opinions in social networks Type de document : texte imprimé Auteurs : Arrar ,Djihad, Auteur ; Refoufi, Allaoua, Directeur de thèse Editeur : Setif:UFA Année de publication : 2021 Importance : 1 vol (63 f .) Format : 29 cm Langues : Français (fre) Catégories : Thèses & Mémoires:Informatique Mots-clés : sentiment analysis Machine learning Deep learning Index. décimale : 004 - Informatique Résumé : Sentiment analysis ( opinion mining) is one of the key tasks of NLP (Natural Language Processing)that tries to infer people’s sentiments as expressed in text documents. Sentiment analysis can be expressed explicitly or implicitly. Most research focus in explicit sentiment analysis,however implicit sentiment analysis has been overlooked and we believe that implicit opinions may carry more insight and convey more information contained in the messages; this thesis tries to close the gap into this less known area of research. In this work, we use machine learning approach and natural language processing techniques to understand the patterns and characteristics of reviews and predict the sentiment . Specifically, we build a computational model that can classify a given review as either positive, negative based on the sentiments it reflects. In this thesis, we also compared our best deep learning model, with our implemented machine learning methods . Indeed our LSTM architecture outperformed them all with a score of 84.2 %. Côte titre : MAI/0471 En ligne : https://drive.google.com/file/d/1HbdKsZxJ8_DKHpXNeZiha7zzixTjPB_1/view?usp=shari [...] Format de la ressource électronique : pdf Analysis of implicit opinions in social networks [texte imprimé] / Arrar ,Djihad, Auteur ; Refoufi, Allaoua, Directeur de thèse . - [S.l.] : Setif:UFA, 2021 . - 1 vol (63 f .) ; 29 cm. Langues : Français (fre) Catégories : Thèses & Mémoires:Informatique Mots-clés : sentiment analysis Machine learning Deep learning Index. décimale : 004 - Informatique Résumé : Sentiment analysis ( opinion mining) is one of the key tasks of NLP (Natural Language Processing)that tries to infer people’s sentiments as expressed in text documents. Sentiment analysis can be expressed explicitly or implicitly. Most research focus in explicit sentiment analysis,however implicit sentiment analysis has been overlooked and we believe that implicit opinions may carry more insight and convey more information contained in the messages; this thesis tries to close the gap into this less known area of research. In this work, we use machine learning approach and natural language processing techniques to understand the patterns and characteristics of reviews and predict the sentiment . Specifically, we build a computational model that can classify a given review as either positive, negative based on the sentiments it reflects. In this thesis, we also compared our best deep learning model, with our implemented machine learning methods . Indeed our LSTM architecture outperformed them all with a score of 84.2 %. Côte titre : MAI/0471 En ligne : https://drive.google.com/file/d/1HbdKsZxJ8_DKHpXNeZiha7zzixTjPB_1/view?usp=shari [...] Format de la ressource électronique : pdf

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
MAI/0471	MAI/0471	Mémoire	Bibliothéque des sciences	Anglais	Disponible Disponible

---

1 (1 - 1 / 1)