In, short am using time use data and I am aiming to represent the way everyday activities connect in time and space.

So i created the above graph in Gephi. The nodes are activities and edges are 2nd order Markov chain probabilities. To make the graph 'clearer' the above graph includes 20 nodes with the highest transition probabilities. In other words loops are removed and other probabilities.

enter image description here

Using R igraph walktrap I clustered the above graph. Is there a way to run cluster analysis in Gephi?

enter image description here However I would like to characterise the clusters with socio-demographics - as suggested one way is to do this is with exponential random graph? Is this the case and if yes - how should I do this?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.