Databases Reference
In-Depth Information
Figure 10-1. Example of the Arabic blogosphere
analysis that convinces us these pictures really are showing us some‐
thing. We put an effort into interpreting the content qualitatively.
So, for example, in the French blogosphere, we see a cluster that dis‐
cusses gourmet cooking. In Germany we see various clusters discus‐
sing politics and lots of crazy hobbies. In English blogs we see two big
clusters [Cathy/mathbabe interjects: gay porn and straight porn?].
They turn out to be conservative versus liberal blogs.
In Russia, their blogging networks tend to force people to stay within
the networks, which is why we see very well-defined, partitioned
clusters.
The proximity clustering is done using the
Fruchterman-Reingold al‐
gorithm
, where being in the same neighborhood means your neigh‐
bors are connected to other neighbors, so really it reflects a collective
