Identification of Influential Users in Emerging Online Social Networks Using Cross-Site Linking

Qingyuan Gong, Yang Chen, Xinlei He, Fei Li, Yu Xiao, Pan Hui, Xin Wang, Xiaoming Fu

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

1 Citation (Scopus)

Abstract

Online social networks (OSNs) have become a commodity in our daily-life. Besides the dominant platforms such as Facebook and Twitter, several emerging OSNs have been launched recently, where users may generate less activity data than on dominant ones. Identifying influential users is critical for the advertisement and the initial development of the emerging OSNs. In this work, we investigate the identification of potential influential users in these emerging OSNs. We build a supervised machine learning-based system by leveraging the widely adopted cross-site linking function, which could overcome the limitations of referring to the user data of a single OSN. Based on the collected real data from Twitter (a dominant OSN) and Medium (an emerging OSN), we show that our system is able to achieve an F1-score of 0.701 and an AUC of 0.755 in identifying influential users on Medium using the Twitter data only.
Original languageEnglish
Title of host publicationComputer Supported Cooperative Work and Social Computing
EditorsYuqing Sun, Tun Lu, Xiaolan Xie, Liping Gao, Liping Gao, Hongfei Fan
Pages331-341
Number of pages11
ISBN (Electronic)978-981-13-3044-5
DOIs
Publication statusPublished - 11 Dec 2018
MoE publication typeA4 Article in a conference publication
EventCCF Conference on Computer Supported Cooperative Work and Social Computing - Guilin, China
Duration: 18 Aug 201819 Aug 2018
Conference number: 13

Publication series

NameCommunications in Computer and Information Science
Volume917
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

ConferenceCCF Conference on Computer Supported Cooperative Work and Social Computing
Abbreviated titleChineseCSCW
CountryChina
CityGuilin
Period18/08/201819/08/2018

Keywords

  • influential users
  • emerging online social networks
  • cross-site linking

Fingerprint Dive into the research topics of 'Identification of Influential Users in Emerging Online Social Networks Using Cross-Site Linking'. Together they form a unique fingerprint.

Cite this