ITE Transactions on Media Technology and Applications
Online ISSN : 2186-7364
ISSN-L : 2186-7364
Special Section on Advanced Imaging and Computer Graphics Technology
[Paper] Personalized Recommendation of Tumblr Posts Using Graph Convolutional Networks with Preference-aware Multimodal Features
Kazuma OhtomoRyosuke HarakawaTakahiro OgawaMiki HaseyamaMasahiro Iwahashi
Author information

2021 Volume 9 Issue 1 Pages 54-61


Tumblr is a popular micro-blogging service on which users can share posts comprising text and images. This paper presents a method for personalizing post recommendations for each user from a large number of posts. Specifically, we develop a supervised multi-variational auto encoder considering user preference (SMVAE-UP). SMVAE-UP can extract relationships between text and image features by considering class information representing a user's preference for each post; thus, preference-aware multimodal features can be calculated. Furthermore, for each target user, a network that enables comparison between a user and posts in the same feature space is constructed using the preference-aware multimodal features and metadata on posts. By applying graph convolutional networks (GCNs) to the network constructed for each target user, an accurate recommendation matching each user's preferred posts becomes feasible. Experimental results for real-world datasets including six users and 99,844 posts show the effectiveness of our method.

Content from these authors
© 2021 The Institute of Image Information and Television Engineers
Previous article Next article