Browse by author
Lookup NU author(s): Dr Nick Hajli
Full text for this publication is not currently held within this repository. Alternative links are provided below where available.
This study utilizes the critical properties of a complex social network to reveal its intrinsic characteristics and the laws governing the way information propagates across the network to identify the central, active users and opinion leaders. The hypernetwork method is applied to analyze user ratings in social networks (SNSs). After introducing the concept of a hypernetwork and its topological characteristics such as node degree, the strength of the node and node hyperdegree, collaborative recommendations in hypernetworks are formulated based on the topological characteristics. Finally, the new method developed is applied to analyze data from theDoubansocial network. In this hypernetwork, users are defined as hyperedges and the objects as nodes. Three hypernetworks focused on reviews of books, movies and music were constructed using the proposed method and found to share a similar law of trends. These topological characteristics are clearly an effective way to reflect the relationship between users and objects. This research will enable SNSs providers to offer better object resource management and a personalized service for users, as well as contributing to empirical analyses of other similar SNSs.
Author(s): Suo Q, Sun S, Hajli N, Love P
Publication type: Article
Publication status: Published
Journal: Expert Systems with Applications
Year: 2015
Volume: 42
Issue: 21
Pages: 7317-7325
Print publication date: 30/11/2015
Online publication date: 29/05/2015
Acceptance date: 26/05/2015
ISSN (print): 0957-4174
ISSN (electronic): 1873-6793
Publisher: Elsevier
URL: http://dx.doi.org/10.1016/j.eswa.2015.05.054
DOI: 10.1016/j.eswa.2015.05.054
Altmetrics provided by Altmetric