Why a user prefers an artwork: A deep attention model for artwork recommendation

The combination of art market and emerging e-commerce has brought new trade opportunities and has achieved continuous growth in recent years. More and more people, especially young people, are keen to browse art information and buy artwork on the Internet. Therefore, designing an effective method of...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of information science Jg. 50; H. 5; S. 1195 - 1210
Hauptverfasser: Tian, Zhiqiang, Liu, Yezheng, Sun, Jianshan, Zhang, Xue, Jiang, Yuanchun
Format: Journal Article
Sprache:Englisch
Veröffentlicht: London, England SAGE Publications 01.10.2024
Bowker-Saur Ltd
Schlagworte:
Aesthetics
Art markets
Art works
Attention
Electronic commerce
Experiments
Internet
Markets
Trade
User experience
Young adults
Youth
Artwork recommendation
deep learning
attention model
image aesthetic
ISSN:0165-5515, 1741-6485
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The combination of art market and emerging e-commerce has brought new trade opportunities and has achieved continuous growth in recent years. More and more people, especially young people, are keen to browse art information and buy artwork on the Internet. Therefore, designing an effective method of recommending artworks may not only effectively enhance the user experience in the art market but also benefit the greater transaction growth. The artwork recommendation task in e-commerce has not received much attention. Previous research works often regard the artworks as ordinary pictures and do not take into account the particularity of the artwork. To solve this problem, we modelled the aesthetic features into artwork recommendation and used the attention mechanism to learn user preferences for various features. We proposed a DAAR (Deep Attention Artwork Recommendation) model and used the attention mechanism to model the user’s preference weights for different features (including content features, aesthetic features and authors). To verify the validity of the proposed model, we collected data and conducted experiments on a real artwork community website. The experimental results show that the proposed DAAR model was better than the current state-of-the-art recommendation methods.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0165-5515
1741-6485
DOI:10.1177/01655515221116511