Comparison of multiple different overlapping community discovery algorithms Online publication date: Thu, 13-Feb-2020
by Weihua Li
International Journal of Web Based Communities (IJWBC), Vol. 16, No. 1, 2020
Abstract: When analysing a real-world problem, it can be transformed into a complex network, and then its structure is divided to find out the overlapping part and study the hidden laws. In this paper, three overlapping community recognition algorithms are briefly introduced, i.e., overlapping community partitioning based on label propagation (OCPLP), footpad skin optical clearing agent (FSOCA) and the genetic algorithm (GA), and then the three artificial networks generated by the LFR tool are simulated and analysed through matrix laboratory (MATLAB) software. The results show that the increase of network complexity will reduce the recognition performance of the three algorithms. In the three algorithms, GA is relatively less affected, which always has the highest recognition performance. OCPLP is the most affected, which has the worst performance. In terms of the speed of recognition, GA is also the fastest, and OCPLP is the slowest. In summary, GA is more suitable for the search of overlapping communities in the network than that of OCPLP and FSOCA.
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Web Based Communities (IJWBC):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email subs@inderscience.com
Our Blog 
Follow us on Twitter 
Visit us on Facebook