Sign In

Communications of the ACM

ACM TechNews

Harnessing the Predictive Power of Virtual Communities

View as: Print Mobile App Share:
Lovro Subelji

Lovro Subelji

Credit: University of Ljubljana

University of Ljubljana researchers say they have developed an algorithm that can detect virtual communities better than existing state-of-the-art algorithms.

The propagation-based algorithm can extract both link-density and link-pattern communities without any prior knowledge of the number of communities. Classical communities are defined by their internal level of link density, while link-pattern communities are characterized by internal patterns of similar connectedness between their nodes.

Ljubljana's Lovro Subelj and Marko Bajec tested the algorithm on 10 real-life networks, including social, information, and biological networks, and concluded that real-life networks appear to be composed of link-pattern communities that are interwoven and overlap with classical link-density communities.

They hope to create a generic model to understand the conditions, such as the low level of clustering, for link-pattern communities to emerge, compared to link-density communities. The researchers say the model could be used to predict future friendships in online social networks, analyze interactions in biological systems that are hard to observe, and detect duplicated code in software systems.

From AlphaGalileo 
View Full Article

Abstracts Copyright © 2012 Information Inc. External Link, Bethesda, Maryland, USA 


No entries found