A hybrid time-series link prediction framework for large social network

Zhu, Jia, Xie, Qing and Chin, Eun Jung (2012). A hybrid time-series link prediction framework for large social network. In: Stephen W. Liddle, Klaus-Dieter Schewe, A Min Tjoa and Xiaofang Zhou, Database and Expert Systems Applications: 23rd International Conference, DEXA 2012, Proceedings, Part II. 23rd International Conference on Database and Expert Systems Applications (DEXA 2012), Vienna, Austria, (345-359). 3-6 September 2012.


Author Zhu, Jia
Xie, Qing
Chin, Eun Jung
Title of paper A hybrid time-series link prediction framework for large social network
Conference name 23rd International Conference on Database and Expert Systems Applications (DEXA 2012)
Conference location Vienna, Austria
Conference dates 3-6 September 2012
Proceedings title Database and Expert Systems Applications: 23rd International Conference, DEXA 2012, Proceedings, Part II   Check publisher's open access policy
Journal name Lecture Notes in Computer Science   Check publisher's open access policy
Place of Publication Heidelberg, Germany
Publisher Springer
Publication Year 2012
Sub-type Fully published paper
ISBN 9783642325960
9783642325977
ISSN 0302-9743
1611-3349
Editor Stephen W. Liddle
Klaus-Dieter Schewe
A Min Tjoa
Xiaofang Zhou
Volume 7447
Start page 345
End page 359
Total pages 15
Collection year 2013
Language eng
Abstract/Summary With the fast growing of Web 2.0, social networking sites such as Facebook, Twitter and LinkedIn are becoming increasingly popular. Link prediction is an important task being heavily discussed recently in the area of social networks analysis, which is to identify the future existence of links among entities in the social networks so that user experiences can be improved. In this paper, we propose a hybrid time-series link prediction model framework called DynamicNet for large social networks. Compared to existing works, our framework not only takes timing as consideration by using time-series link prediction model but also combines the strengths of topological pattern and probabilistic relational model (PRM) approaches. We evaluated our framework on three known corpora, and the favorable results indicated that our proposed approach is feasible.
Q-Index Code C1
Q-Index Status Confirmed Code
Institutional Status UQ

 
Versions
Version Filter Type
Citation counts: Google Scholar Search Google Scholar
Access Statistics: 83 Abstract Views  -  Detailed Statistics
Created: Mon, 24 Sep 2012, 11:44:22 EST by Ms Imogen Ferrier on behalf of School of Information Technol and Elec Engineering