On Oct 14, 2010, at 3:28 PM, Roy Tennant wrote: > ...I went to the data mining workshop with my librarian hat on and > was quickly disabused of my notions of mining out personal names, > locations, etc., from large piles of text. Nope. It was pretty > much all about word frequency, etc...
Yep, word (ngram) frequency, concordances, and visualization of same. This is some of what the digital humanists like to do. They also like to do "stylometry" -- figuring out who was the author of such and such work by analyzing what words were used and in what ways. "Is Shakespeare the author of this newly discovered sonnet?" Given the increasingly HUGE amounts of full texts available in libraries, I think the application of digital humanities computing techniques can easily be integrated into library applications. Put another way, I think our Code4Lib community is uniquely placed between some of the computer scientists and the digital humanists. Both the computer scientists and the digital humanists are keenly interested in libraries and library work as exemplified by the ECDL/JCDL and Digital Humanities conferences. [1, 2] Us Code4Lib'ers can implement the things the academics on both sides of us are researching. I was (hoping) wondering if any of the library folks who attended #thatcampsf saw similar synergies. [1] DH 2010 travelogue - http://bit.ly/9cNj4z [2] ECDL 2010 travelogue - http://bit.ly/dB1vm3 -- Eric "Budding Digital Humanist" Morgan University of Notre Dame
