Here's a link to a page from a text mining book that discusses how to determine the number of clusters to choose for k-means clustering.
http://nlp.stanford.edu/IR-book/html/htmledition/cluster-cardinality-in-k-means-1.html
We'll talk about a couple of clustering techniques that aren't covered in the book. Here are links to the papers where they are described.
Canopy clustering:
Association Propagation Clustering:
original paper - FreyDueckScience07.pdf
ap clustering on large data - apClusterLargeData.pdf