Text Analytics Conference

From the website..

"The 2nd Annual Text Analytics Summit 2006 is taking place 22 - 23 June, 2006 in Boston. If you're a user of text analytics technology in any application or industry, this is an unmissable opportunity to learn from your peers and understand the bottom-line impact of the latest deployments. If you're a developer, this is your chance to meet a market focused on text analytics and exchange strategies for success with industry peers."

What is text mining?

Rb

Text mining is the extraction of information from unstructured, electronically accessible text resources. It is a particularly important area of bioinformatics because of the vast size of the scientific literature. A nice example of a useful application created via text mining is called iHOP - information Hyperlinked Over Proteins. iHOP was produced by identifying thousands of protein names in PubMed documents and then linking the documents that shared proteins together. This makes it possible to 1) quickly display most of the relevant textual information about a particular protein in one location and 2) browse the literature by "hopping" from paper to paper along gene-based hyperlinks.

In a way, every time you do a search on Google or on PubMed you are doing a little text mining, but the field is generally concerned with more automated methods for extracting knowledge from large sources of unstructured (no XML tags, not a database..) text.