[Sigia-l] automated content clustering?

[eric scheid]

What's the current state of play for automated content clustering?

I'm looking at a project where the client has about 1,500 documents and only
a very coarse high-level category scheme. We've got to come up with a full
category hierarchy to put all this content into. We've got a few ideas
already, but I'm wondering if automated content clustering has come along
over the years and may thus be an option worth investigating.

Anyone have experience here?

eric.