Exploring the power of social hub services

Qingyuan Gong, Yang Chen*, Xiaolong Yu, Chao Xu, Zhichun Guo, Yu Xiao, Fehmi Ben Abdesslem, Xin Wang, Pan Hui

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

2 Citations (Scopus)

Abstract

Given the diverse focuses of emerging online social networks (OSNs), it is common that a user has signed up on multiple OSNs. Social hub services, a.k.a., social directory services, help each user manage and exhibit her OSN accounts on one webpage. In this work, we conduct a data-driven study by crawling over one million user profiles from about.me, a representative online social hub service. Our study aims at gaining insights on cross-OSN social influence from the crawled data. We first analyze the composition of the social hub users. For each user, we collect her social accounts from her social hub webpage, and aggregate the content generated by these accounts on different OSNs to gain a comprehensive view of this user. According to our analysis, there is a high probability that a user would provide consistent information on different OSNs. We then explore the correlation between user activities on different OSNs, based on which we propose a cross-OSN social influence prediction model. With the model, we can accurately predict a user’s social influence on emerging OSNs, such as Instagram, Foursquare, and Flickr, based on her data published on well-established OSNs like Twitter.

Original languageEnglish
Pages (from-to)2825–2852
Number of pages28
JournalWorld Wide Web
Volume22
Issue number6
Early online date1 Jan 2018
DOIs
Publication statusPublished - Nov 2019
MoE publication typeA1 Journal article-refereed

Keywords

  • Machine learning
  • Measurement
  • Online social networks
  • Social hub services
  • Social influence

Fingerprint

Dive into the research topics of 'Exploring the power of social hub services'. Together they form a unique fingerprint.

Cite this