Leveraging Image Visual Features in Content-Based Recommender System

Content-based (CB) and collaborative filtering (CF) recommendation algorithms are widely used in modern e-commerce recommender systems (RSs) to improve user experience of personalized services. Item content features and user-item rating data are primarily used to train the recommendation model. Howe...

Full description

Saved in:
Bibliographic Details
Published in:Scientific programming 2018-01, Vol.2018 (2018), p.1-8
Main Authors: Huang, Gu, Qin, Zhen, Ren, Panlong, Deng, Fuhu, Qin, Zhiguang
Format: Article
Language:English
Subjects:
Algorithms
Collaboration
Datasets
Electronic commerce
Experiments
Filtration
Information systems
International conferences
Motion pictures
Neural networks
Ratings & rankings
Recommender systems
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Content-based (CB) and collaborative filtering (CF) recommendation algorithms are widely used in modern e-commerce recommender systems (RSs) to improve user experience of personalized services. Item content features and user-item rating data are primarily used to train the recommendation model. However, sparse data would lead such systems unreliable. To solve the data sparsity problem, we consider that more latent information would be imported to catch users’ potential preferences. Therefore, hybrid features which include all kinds of item features are used to excavate users’ interests. In particular, we find that the image visual features can catch more potential preferences of users. In this paper, we leverage the combination of user-item rating data and item hybrid features to propose a novel CB recommendation model, which is suitable for rating-based recommender scenarios. The experimental results show that the proposed model has better recommendation performance in sparse data scenarios than conventional approaches. Besides, training offline and recommendation online make the model has higher efficiency on large datasets.
ISSN:1058-9244
1875-919X
DOI:10.1155/2018/5497070