A cluster-based opinion leader discovery in social network

Yi Cheng Chen, Ju Ying Cheng, Hui Huang Hsu

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

17 Scopus citations

Abstract

Recently, opinion leader discovery has drawn much attention due to its widespread applicability. By identifying the opinion leader, companies or governments can manipulate the selling or guiding public opinion, respectively. However, mining opinion leader is a challenge task because of the complexity of processing social graph and analyzing leadership quality. In this study, a novel method, TCOL-Miner, is proposed to efficiently find the opinion leaders from a huge social network. We integrate the clustering and semantic analysis methods with some pruning strategies to tackle the influence overlapping issue and the potential leadership of individuals. The experimental results show that the proposed TCOL-Miner can effectively discover the influenced opinion leaders in different real social networks with efficiency.

Original languageEnglish
Title of host publicationTAAI 2016 - 2016 Conference on Technologies and Applications of Artificial Intelligence, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages78-83
Number of pages6
ISBN (Electronic)9781509057320
DOIs
StatePublished - 16 Mar 2017
Event2016 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2016 - Hsinchu, Taiwan
Duration: 25 Nov 201627 Nov 2016

Publication series

NameTAAI 2016 - 2016 Conference on Technologies and Applications of Artificial Intelligence, Proceedings

Conference

Conference2016 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2016
Country/TerritoryTaiwan
CityHsinchu
Period25/11/1627/11/16

Keywords

  • clustering
  • opinion Leader
  • semantic analysis
  • social network

Fingerprint

Dive into the research topics of 'A cluster-based opinion leader discovery in social network'. Together they form a unique fingerprint.

Cite this