When you compress a text document using a ZIP application, the degree to which it compresses is distinctive and varies depending on the language the document was written in. The upshot is that the results of ZIP operations can be used to automatically identify a pool of documents' languages.
The researchers found that file compression analysis worked well in identifying the language of files as short as twenty characters in length, and could correctly sort books by author more than 93% of the time.
(Thanks, Dennis!)
