Data Story: Gephi - Clustering layout by modularity

Modularity is one measure of the structure of networks or graphs. It was designed to measure the strength of division of a network into modules (also called groups, clusters or communities). Networks with high modularity have dense connections between the nodes within modules but sparse connections between nodes in different modules. Modularity is often used in optimization methods for detecting community structure in networks.

However, it has been shown that modularity suffers a resolution limit and, therefore, it is unable to detect small communities. Biological networks, including animal brains, exhibit a high degree of modularity.

Gephi uses Louvain method for calculating modularity and one thing to note is that high modularity doesn't denote "good" partition. Some discussions from Gephi are listed below:

Indeed you can't use the raw modularity scores to say whether it is a "good" partition, because a similarly high score may also be obtained in a random graph. Compare it to the traditional clustering coefficient: if the two variables are independent (the 'null' condition), the correlation is zero, so any correlation away from zero is "high". For modularity however, this value is not zero for random graphs (the 'null' condition), so that it's difficult to say whether modularity is 'high' and therefore a 'good' partition. ->link

We removed it because it was wrong. One can show how to generate a random graph with a high Q value. Hence Q can't be used to interpret how significant the communities are. ->link

How to get the clustering layout by modularity?

Step 1. Calculate Modularity [Statistics] -> Modularity [Run]

Step 2. Apply Filter [Attributes] -> [Partition] -> [Modularity Class]
- Select first partition and click [Filter], then nodes in first modularity class will be left.