preprintJan 30, 2019GREEN OA

Session-Based Social Recommendation via Dynamic Graph Attention Networks

WSWeiping SongZXZhiping XiaoYWYifan WangLCLaurent CharlinMZMing Zhang

Peking University · University of California, Berkeley · +1 more institution

Indexed inarxivcrossref

Abstract

Online communities such as Facebook and Twitter are enormously popular and have become an essential part of the daily life of many of their users. Through these platforms, users can discover and create information that others will then consume. In that context, recommending relevant information to users becomes critical for viability. However, recommendation in online communities is a challenging problem: 1) users' interests are dynamic, and 2) users are influenced by their friends. Moreover, the influencers may be context-dependent. That is, different friends may be relied upon for different topics. Modeling both signals is therefore essential for recommendations. We propose a recommender system for online…

Citation impact

465
total citations
FWCI
89.56
Percentile
100%
References
55
Citations per year

Authors

6

Topics & keywords

Topics
Keywords
  • Influencer marketing
  • Computer science
  • Recommender system
  • Session (web analytics)
  • Graph
  • Context (archaeology)
  • Social network (sociolinguistics)
  • Social graph
No related works found for this paper.

Funding