Enhancing a Content-Based Recommender System using Deep Learning for Online Resources / hanane Bouaziz  

Public ISBD Titre : Enhancing a Content-Based Recommender System using Deep Learning for Online Resources Type de document : texte imprimé Auteurs : hanane Bouaziz, Auteur ; meriem Deghmoum, Auteur ; Mediani,Chahrazed, Directeur de thèse Année de publication : 2023 Importance : 1 vol (52 f .) Format : 29cm Langues : Français (fre) Catégories : Thèses & Mémoires:Informatique Mots-clés : Recommender system content-based Index. décimale : 004 Informatique Résumé : In light of the expansion of digital content and the escalating need for personalized recommendations, recommender systems have emerged as essential tools in facilitating user exploration and involvement. Among the different approaches available, content-based recommender systems utilize the inherent attributes of items to produce recommendations. in This thesis we present the design and implementation of a deep learning-based content-based recommender system. We explore different deep learning architectures, including TF-IDF,Word2Vec, TF-IDF with Logistic Regression,Word2Vec with Logistic Regression, and LSTM models, to capture item and user preferences from the available data. These models are evaluated using precision, recall, and F1-score metrics to assess their performance in recommending relevant items. with the goal of improving the quality and performance of such systems. Côte titre : MAI/0705 En ligne : https://drive.google.com/file/d/1LmOPrce-ApSpOeoLja6XBN8Rcb-k-uAH/view?usp=drive [...] Format de la ressource électronique : pdf Enhancing a Content-Based Recommender System using Deep Learning for Online Resources [texte imprimé] / hanane Bouaziz, Auteur ; meriem Deghmoum, Auteur ; Mediani,Chahrazed, Directeur de thèse . - 2023 . - 1 vol (52 f .) ; 29cm. Langues : Français (fre) Catégories : Thèses & Mémoires:Informatique Mots-clés : Recommender system content-based Index. décimale : 004 Informatique Résumé : In light of the expansion of digital content and the escalating need for personalized recommendations, recommender systems have emerged as essential tools in facilitating user exploration and involvement. Among the different approaches available, content-based recommender systems utilize the inherent attributes of items to produce recommendations. in This thesis we present the design and implementation of a deep learning-based content-based recommender system. We explore different deep learning architectures, including TF-IDF,Word2Vec, TF-IDF with Logistic Regression,Word2Vec with Logistic Regression, and LSTM models, to capture item and user preferences from the available data. These models are evaluated using precision, recall, and F1-score metrics to assess their performance in recommending relevant items. with the goal of improving the quality and performance of such systems. Côte titre : MAI/0705 En ligne : https://drive.google.com/file/d/1LmOPrce-ApSpOeoLja6XBN8Rcb-k-uAH/view?usp=drive [...] Format de la ressource électronique : pdf

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
MAI/0705	MAI/0705	Mémoire	Bibliothéque des sciences	Anglais	Disponible Disponible

---

1 (1 - 1 / 1)