Detecting Commmunities via Simultaneous Clustering of Graphs and Folksonomies

Great news! Our WebKDD 2008 submission titled "Detecting Commmunities via Simultaneous Clustering of Graphs and Folksonomies" was accepted. I received a number of very helpful comments and suggestions from the reviewers and I am working on updating the paper. I will make the pre-print version available on the ebiquity site as soon as it is ready. In the mean time here is the abstract for this paper:

We present a simple technique for detecting communities by utilizing both the link structure and folksonomy (or tag) information that is readily available in most social media systems. A simple way to describe our approach is by defining a community as a set of nodes in a graph that link more frequently to within this set than outside it and they share similar tags. Our technique is based on the Normalized Cut (NCut) algorithm and can be easily and efficiently implemented. We validate our method by using a real network of blogs and tag information obtained from a social bookmarking site. We also verify our results on a citation network for which we have access to ground truth cluster information. Our method, Simultaneous Cut (SimCut), has the advantage that it can group related tags and cluster the nodes simultaneously.

Interestingly, I had discussed some of the basic idea behind this paper in my earlier blog post "Clustering Tags and Links Simultaneously."