Print

Print


*****  To join INSNA, visit http://www.insna.org  *****



Recently I have been working on new clustering algorithms, focusing on those that allow for overlap/intersection between found clusters/communities.

Working with various smart people, it is amazing that we all came up with good answers, but we all wondered who has the best answer?  And then, after some reflection... Is there a BEST answer  in cluster-finding, community detection?

Smart people disagree in many fuzzy domains... here also?  Below is a blog post that examines some of the clusters found in a simple toy network.  Which ones do you like?  Is there one that is "obviously" better than the others? Have we missed an obvious set of clusters?

www.thenetworkthinkers.com/2013/11/making-sense-of-emergent-patterns-in.html 

Here is a link list of the data used in the above blog post.  Would be happy to see other results and the thinking behind them!

 FROM,TO
1,2
1,3
1,4
1,10
1,13
1,14
1,16
2,1
2,3
2,6
2,13
2,14
3,1
3,2
3,13
4,1
4,5
4,7
4,12
4,14
4,15
4,16
5,4
5,6
5,9
5,14
5,15
6,2
6,5
6,14
7,4
7,8
7,15
8,7
8,9
8,15
9,5
9,8
9,15
10,1
10,11
10,16
11,10
11,12
11,16
12,4
12,11
12,16
13,1
13,2
13,3
14,1
14,2
14,4
14,5
14,6
15,4
15,5
15,7
15,8
15,9
16,1
16,4
16,10
16,11
16,12

Valdis Krebs
Orgnet, LLC
Twitter: orgnet
http://orgnet.com
http://thenetworkthinkers.com



_____________________________________________________________________
SOCNET is a service of INSNA, the professional association for social
network researchers (http://www.insna.org). To unsubscribe, send
an email message to [log in to unmask] containing the line
UNSUBSCRIBE SOCNET in the body of the message.