In the fall of 2004 I began experimenting with different concept-based feature representations for automatic text classification and clustering tasks using the NC Health Info community health website collection as a corpus. The goal is to automate the generation of both index & topic term sets for information architecture tasks with the ultimate hope of creating a cataloguing workstation and website topic menu generator. NC Health Info is a joint project of SILS and UNC Health Sciences Library that is funded by a grant from the National Library of Medicine. My research advisor is Dr. Stephanie Haas.