[igraph] Choosing between different methods of detecting communities

[Roey Angel]

Hi,
I've constructed an undirected network of some 1500 nodes, and then 
applied to it different methods of community detection (Walktrap, 
Fastgreedy, label propagation and leading eigenvector). Not surprisingly 
the different methods give somewhat different results (different numbers 
of communities, different membership patterns etc.).
I was wondering if there's a way to choose between the methods, either 
by experience (e.g. 'method x typically gives best results) or with some 
statistical test.
I've looked into compare function but couldn't really make sense of it's 
output.
Also, are there any recommendations on how to set the function 
variables. e.g. steps.

Thanks in advance,
Roey

angel.vcf
Description: Vcard