Thursday, February 12, 2009

Science / Shakespeare Crossover : High Geek Factor

http://www.physorg.com/news153595290.html

I am still trying to absorb this aticle, and I have not watched the video yet, but the subject matter is so up my alley that I can’t wait to post it.  It’s all about a technique for analyzing large groups of stuff called “feature frequency profiles”, or FFP.  In theory, you can apply the technique to anything that might have patterns in it – DNA, music taste…and, of course, the works of Shakespeare.

Kim and his colleagues later applied the FFP technique to a comparative analysis of the works of William Shakespeare, contemporaries such as Christopher Marlowe, plus several works from the Jacobean era that were once attributed to Shakespeare but whose authorships are now in question. The results cast new doubt on Shakespeare having been the author of the play Pericles, Prince of Tyre, and point to his authorship of the comedy Two Noble Kinsmen, for which in the past he has only received partial credit.

In that particular case I don’t think of it so much as a discovery, since there’s already been doubt on those plays – but if the FFP algorithm also kicked those out as questionable, without having been told, that’d be pretty impressive.

5 comments:

catkins said...

Duane, what do you mean you haven't watched the video yet, it's only 56 seconds! This looks really cool! I wonder if they ran it on "A Lover's Complaint." I am convinced it is not by Shakespeare. And I always liked "Two Noble Kinsmen."
--Carl

Duane said...

Bro I find these things at work and have to figure out how much time I can spend on the blog without the boss coming around the corner. Watching videos is tricky!

Anonymous said...

Duane, I'm the principal author and researcher who worked on the project that you're trying to absorb. If you're interested in learning more about the process an article describing the work has been published in PNAS (under open access). Our primary purpose was to compare genomic sequences -- the Shakespeare texts were an interesting off-shoot of that work. If you've got any interesting ideas send them my way.

Gregory E. Sims, PhD

Duane said...

Thanks Greg! Downloaded the article, didn't understand a word of it :). Although I did get that FFP is a known, existing technique for text and book comparison, so it sounds like my original guess - that the Shakespeare authorship thing was really more a test of the algorithm than a new discovery - is reasonably accurate.

As a software geek I have to ask, got any source code? :)

Anonymous said...

Duane,

We're putting together something that's user friendly at the moment as part of the publication process. Email me at gesims at lbl dot gov, and I will send you a note of any software release.

Gregory E. Sims, PhD