Skip to main navigation Skip to search Skip to main content

Recommending followees based on content weighted user interest homophily

  • Lifang Wu
  • , Dai Zhang
  • , Xiuzhen Zhang
  • , Yuchen Jing
  • , Haiying Liu
  • , Chang Wen Chen
  • Beijing University of Technology
  • Royal Melbourne Institute of Technology University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

We study the problem of recommending followees to users on content curation social networks (CCSNs). Different from existing friendship-oriented user recommendation approaches, we exploit user interest homophily to recommend users of similar interests, combining the users' social network as well as their topical interests. We first profile users with social links and topical interests derived from "re-pin paths". We further design a collaborative filtering strategy for user recommendation based on interest homophily. Experiments on a content curation social network show that our recommendation algorithm based on user interest homophily performs better than recommendation based on user popularity.

Original languageEnglish
Title of host publicationProceedings of the International Conference on Internet Multimedia Computing and Service, ICIMCS 2016
PublisherAssociation for Computing Machinery
Pages146-151
Number of pages6
ISBN (Electronic)9781450348508
DOIs
StatePublished - Aug 19 2016
Event8th International Conference on Internet Multimedia Computing and Service, ICIMCS 2016 - Xi'an, China
Duration: Aug 19 2016Aug 21 2016

Publication series

NameACM International Conference Proceeding Series
Volume19-21-August-2016

Conference

Conference8th International Conference on Internet Multimedia Computing and Service, ICIMCS 2016
Country/TerritoryChina
CityXi'an
Period08/19/1608/21/16

Keywords

  • Content curation social networks
  • Recommender systems
  • Social recommendation
  • User interest homophily

Fingerprint

Dive into the research topics of 'Recommending followees based on content weighted user interest homophily'. Together they form a unique fingerprint.

Cite this