KANGAROO: A DISTRIBUTED SYSTEM FOR SNA - Social Network Analysis in Huge-Scale Networks

Wu Bin, Dong Yuxiao, Qin Lei, Ke Qing, Wang Bai

2011

Abstract

Social network analysis is the mapping and measuring of relationships and flows between people, groups, computers and other information or knowledge entities. The continued exponential growth in the scale of social networks is giving birth to a new challenge to social network analysis. The scale of these graphs, in some cases, is millions of nodes and billions of edges. In this paper, we present a distributed system, KANGAROO, for huge scale social network based on two main computing models which are for finding common neighbour and maximal clique. KANGAROO is implemented on the top of the Hadoop platform, the open source version of MapReduce. This system implements most algorithms of social network analysis, including basic statistics, community detection, link prediction and network evolution etc. based on the MapReduce computing framework. More than anything else, KANGAROO is applied to a real-world huge scale social network. The application scenarios, including degree distribution, linear projection algorithm for community detection and community visualization of presentation layer, demonstrate KANGAROO is efficient, scalable and effective.

Download


Paper Citation


in Harvard Style

Bin W., Yuxiao D., Lei Q., Qing K. and Bai W. (2011). KANGAROO: A DISTRIBUTED SYSTEM FOR SNA - Social Network Analysis in Huge-Scale Networks . In Proceedings of the 1st International Conference on Cloud Computing and Services Science - Volume 1: CLOSER, ISBN 978-989-8425-52-2, pages 404-409. DOI: 10.5220/0003387304040409

in Bibtex Style

@conference{closer11,
author={Wu Bin and Dong Yuxiao and Qin Lei and Ke Qing and Wang Bai},
title={KANGAROO: A DISTRIBUTED SYSTEM FOR SNA - Social Network Analysis in Huge-Scale Networks},
booktitle={Proceedings of the 1st International Conference on Cloud Computing and Services Science - Volume 1: CLOSER,},
year={2011},
pages={404-409},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003387304040409},
isbn={978-989-8425-52-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 1st International Conference on Cloud Computing and Services Science - Volume 1: CLOSER,
TI - KANGAROO: A DISTRIBUTED SYSTEM FOR SNA - Social Network Analysis in Huge-Scale Networks
SN - 978-989-8425-52-2
AU - Bin W.
AU - Yuxiao D.
AU - Lei Q.
AU - Qing K.
AU - Bai W.
PY - 2011
SP - 404
EP - 409
DO - 10.5220/0003387304040409