Thèses en ligne de l'université 8 Mai 1945 Guelma

A Recommendation System Based On Sentiment Analysis

Afficher la notice abrégée

dc.contributor.author MEHENNAOUI, ZOHRA
dc.date.accessioned 2024-12-02T12:38:56Z
dc.date.available 2024-12-02T12:38:56Z
dc.date.issued 2024
dc.identifier.uri http://dspace.univ-guelma.dz/jspui/handle/123456789/16469
dc.description.abstract The recommendation system is an essential component of multiple domains, such as e-commerce, health care and social media, where it predicts user preferences by providing relevant suggestions. In this work, to improve the performance of the recommender systems, we propose a new approach to recommendation that we have applied on the Yelp Business dataset. This approach is based on sentiment analysis using three Machine Learning (ML) methods: Support Vector Machines (SVM), Naive Bayes (NB), Logistic Regression (LR) and Bidirectional Encoder Representations from Transformers DistilBERT. The proposed approach aims to improve recommendations through sentiment analysis of their user’s reviews. We employ the method of Singular Value Decomposition (SVD) to help treat sparsity in user-item interaction data, ensuring minimum variance results with limited data inputs as well. The results using Neural Collaborative Filtering (NCF) as a recommendation model showed a good performance of the proposed approach, demonstrating its efficiency and accuracy in recommendation tasks. en_US
dc.language.iso en en_US
dc.publisher University of Guelma en_US
dc.subject Recommendation System, Sentiment Analysis, Support Vector Machine, Naive Bayes, Logistic Regression, DistilBERT, SVD, NCF. en_US
dc.title A Recommendation System Based On Sentiment Analysis en_US
dc.type Working Paper en_US


Fichier(s) constituant ce document

Ce document figure dans la(les) collection(s) suivante(s)

Afficher la notice abrégée

Chercher dans le dépôt


Recherche avancée

Parcourir

Mon compte