Skip to main navigation Skip to search Skip to main content

Identifying influential positively perceived users in co-purchase networks

  • Jordan University of Science and Technology

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

4 Scopus citations

Abstract

Identifying influential users is one of the important problems in social network analysis with many useful applications ranging from marketing to epidemics and opinion diffusion (e.g., on political issues). In this paper, we focus on how to determine influential users by correlating different centrality measures with how the users are perceived by their community. Specifically, we work on the Amazon product purchasing data and build a 'co-purchase' network connecting users who purchased the same items. We then identify influential users based on different structural measures (closeness centrality, betweenness centrality, etc.) and analyze the relationship between these measures and the community's perception of the users. Our analysis shows several interesting observations. For example, we observed a high correlation between having a high betweenness centrality and being viewed positively by the community.

Original languageEnglish
Title of host publication2018 9th International Conference on Information and Communication Systems, ICICS 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages78-83
Number of pages6
ISBN (Electronic)9781538643662
DOIs
StatePublished - 4 May 2018
Externally publishedYes
Event9th International Conference on Information and Communication Systems, ICICS 2018 - Irbid, Jordan
Duration: 3 Apr 20185 Apr 2018

Publication series

Name2018 9th International Conference on Information and Communication Systems, ICICS 2018
Volume2018-January

Conference

Conference9th International Conference on Information and Communication Systems, ICICS 2018
Country/TerritoryJordan
CityIrbid
Period3/04/185/04/18

Keywords

  • amazon metadata
  • correlation
  • influence
  • social network analysis

Fingerprint

Dive into the research topics of 'Identifying influential positively perceived users in co-purchase networks'. Together they form a unique fingerprint.

Cite this