Skip to Main content Skip to Navigation
New interface
Theses

Données et industries des contenus, modélisation et prototypage d’un système de recommandation pour le catalogue d’un service d’information documentaire

Abstract : Recommender systems are among the promising fields of machine learning, which haverevolutionized the information retrieval.The context of our thesis is the Moroccan Institute for Scientific and Technical Information(IMIST), having as an objective to design and implement a recommender system based on logdata, according to the collaborative filtering approach.To achieve these objectives, we first began to identify the IMIST's need for a recommendersystem, then we design and carry out a prototype based on user’s implicit data to providerecommendations.It should be noted that it was necessary to convert the implicit data of the users into explicitdata in the form of scores, in order to exploit them.This prototype distinguishes between the anonymous user and the subscriber user.The implementation of the system was done in a Spark environment, using the Scala languageand the ALS Train Implicit model of the matrix factorization.
Complete list of metadata

https://tel.archives-ouvertes.fr/tel-03793337
Contributor : ABES STAR :  Contact
Submitted on : Saturday, October 1, 2022 - 1:07:54 AM
Last modification on : Sunday, October 2, 2022 - 3:48:51 AM

File

CNAM_AmineSENNOUNI_2021.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-03793337, version 1

Citation

Amine Sennouni. Données et industries des contenus, modélisation et prototypage d’un système de recommandation pour le catalogue d’un service d’information documentaire. Sciences de l'information et de la communication. HESAM Université, 2021. Français. ⟨NNT : 2021HESAC034⟩. ⟨tel-03793337⟩

Share

Metrics

Record views

130

Files downloads

11