Unspam Technologies has a way to determine which entrants into the Sundance Film Festival are destined for stardom or the trash bin; they filter film descriptions through a Bayesian spam filter.
If a film is a drama or documentary at Sundance, Unspam has a good shot at determining if it’s going to get attention after the festival. Claiming an 81 percent success rate, Unspam’s CEO Matthew Prince and his staff can make a pretty good guess, with the help of technology, the Los Angeles Times reported.
Prince described how his engineers approached the problem of determining what in email is or is not spam by comparing it with what was or was not successful in film:
“We had the last 10 years of the festival’s film guides, which are like inputs, and then a bunch of outputs, like how many people saw a film, did it win anything at Sundance, did it have commercial success. If you could figure out the pattern between the inputs and the outputs, then you could actually predict future winners.”
Bayesian filtering is a technique used to calculate the probability that a given inbound message is spam or not, according to the Computer Desktop Encyclopedia. Prince and company applied that technique to the Sundance guidebooks, and found they did pretty well at finding the winners in a couple of categories.
They have since set up a dedicated website to host their predictions. The site listed terms that can “make you golden” or be a “kiss of death” when part of a film description:
Golden: Academic, Accomplished, Bedroom, Complex, Dialogue, Dream, Death, Focus, Girl, Human, High, Journey, Love, Mother, Narrative, Romance, Relationship, Superbly, Sex, Ultimately.
Kiss of death: Africa, America, American, Beautiful, Black, Best, Emotional, Fascinating, Great, Inspired, Lake, New, Riveting, Sundance, Sexy, Story, Subtitles, Truth, Vision, World.
Remember, death is good, truth is bad.
—
document.write(“Email the author here.”)
Drag this 
Add to document.write(“Del.icio.us”) | DiggThis | Yahoo My Web
David Utter is a staff writer for Murdok covering technology and business.
