Stan Schroeder at Mashable yesterday highlighted a new effort by Google:
Can humor be quantified? Google thinks it’s possible, having recently developed an algorithm which ranks the funniest videos on YouTube. It takes into account certain elements of the video, user comments and votes on the recently launched YouTube Comedy Slam section of the site.
Google engineer Sanketh Shetty explained the methodology for finding the funniest YouTube video in a blog post.
“We focused on videos uploaded in the comedy category. We captured the uploader’s belief in the funniness of their video via features based on title, description and tags. Viewers’ reactions, in the form of comments, further validate a video’s comedic value,” he wrote.
This is where it gets interesting, as Google engineers tried to analyze what exactly makes a user comment indicative of a video being funny. “We noticed that viewers emphasize their reaction to funny videos in several ways: e.g. capitalization (LOL), elongation (loooooool), repetition (lolololol), exclamation (lolllll!!!!!), and combinations thereof. If a user uses an “loooooool” vs an “loool”, does it mean they were more amused,” asks Shetty.
Which YouTube video, by this method, is the funniest ever? This one:
This did not make me laugh once.
I can get saying, “This is the funniest thing I’ve ever seen.” But I don’t get how anyone can definitively say, “This is the funniest thing ever.” Humor is too personal for that.
What do you think? Can humor be quantified? If so, is Google going about it in the right way? How could the method be improved? Or is it a fool’s game to even try to quantify comedy?
(If you have a suggestion for a QOTD, feel free to email me. Responses to this QOTD sent by email will be ignored; please post your responses here.)