Skip to content. | Skip to navigation

Informatik 5
Information Systems
Prof. Dr. M. Jarke
Sections
Personal tools
You are here: Home Publications Analysis of Overlapping Communities in Signed Complex Networks

Contact

Prof. Dr. M. Jarke
RWTH Aachen
Informatik 5
Ahornstr. 55
D-52056 Aachen
Tel +49/241/8021501
Fax +49/241/8022321

How to find us

Annual Reports

Disclaimer

Webmaster

 

 

Analysis of Overlapping Communities in Signed Complex Networks

Year 2016

Networks with positive and negative connections have gained popularity in social media. Positive links show trust (friendship) and negative connections are sign of distrust(enmity). An instance of such networks is Wikipedia, in which some contributors are promoted to administrators by other Wikipedia users. Similar to unsigned networks, overlapping communities are pivotal structures, giving much of opportunities to reveal useful information from signed networks. Detection of communities in this area is not well studied, which is currently almost impossible to select a good algorithm for recommender or analytic systems. In this paper, we perform a multifaceted analysis of overlapping community detection algorithms and compare them from different aspects; computing modularity, frustration, running time as for the metrics. This work assists social network analysis researchers to select a suitable algorithm for their systems, e.g. recommender systems.

Authors

Published in

Proceedings of the workshop on Recommender Systems and Big Data Analytics (RS-BDA’16); CEUR-i-KNOW2016 .

Related projects

Document Actions