Deep Learning for Visual-Features Extraction Based Personalized User Modeling

Personalized Recommender Systems help users to choose relevant resources and items from many choices, which is an important challenge that remains actuality today. In recent years, we have witnessed the success of deep learning in several research areas, such as computer vision, natural language pro...

Full description

Saved in:
Bibliographic Details
Published in:SN computer science 2022-07, Vol.3 (4), p.261, Article 261
Main Authors: Ben Hassen, Aymen, Ben Ticha, Sonia, Chaibi, Anja Habacha
Format: Article
Language:English
Subjects:
Algorithms
Collaboration
Computer Imaging
Computer Science
Computer Systems Organization and Communication Networks
Computer vision
Customization
Data Structures and Information Theory
Datasets
Deep learning
Filtration
Image processing
Information Systems and Communication Service
Motion pictures
Natural language processing
Neural networks
Original Research
Pattern Recognition and Graphics
Recommender systems
Software Engineering/Programming and Operating Systems
Vision
Web Information Systems and Technologies 2021
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Personalized Recommender Systems help users to choose relevant resources and items from many choices, which is an important challenge that remains actuality today. In recent years, we have witnessed the success of deep learning in several research areas, such as computer vision, natural language processing, and image processing. In this paper, we present a new approach exploiting the images describing items to build a new user’s personalized model. With this aim, we use deep learning to extract and reduction dimensionality of latent features describing images. Then we associate these latents features with user preferences to build the personalized model. This model was used in a Collaborative Filtering (CF) algorithm to make recommendations. Experimentally, to evaluate our approach, we apply our approach on two large real data of differents domains, such as fashion and movies, using fashion data sets from Amazon.com and movies data sets from MovieLens, where we show that the best performance of clothing image is more important than the poster of a movie, which explains that the fashion image has an importance in the preferences of the users. Finally, we compare our results to other approaches based on collaborative filtering algorithms.
ISSN:2661-8907
2662-995X
2661-8907
DOI:10.1007/s42979-022-01131-y