Well, I think that this is proof-positive that the programmers and algorithm writers who control many aspects of our lives–from our search engines, to our smart phones, to our GPS devices–may be on a plane of intelligence far above the rest of us, but they still haven’t cracked the code of what makes humans human. Will they ever? Of course, this has been a topic fiercely debated ever since the rise of the concept of “artificial intelligence,” but I’ve always been a skeptic. It seems to me that you can’t quantify that many vagaries and mysteries of the human experience, especially our emotions.
But the programmers at Google are trying their best, regardless. A team of researchers there recently tried to quantify comedy–what makes us laugh. By tallying up the number of “LOLs” and other humor indicators that appear in the comments section of YouTube videos, the researchers came up with a list of the so-called funniest videos on the web.
Here’s Google on how the researchers devised the algorithm:
- In a previous post, we talked about quantification of musical talent using machine learning on acoustic features forYouTube Music Slam. We wondered if we could do the same for funny videos, i.e. answer questions such as: is a video funny, how funny do viewers think it is, and why is it funny? We noticed a few audiovisual patterns across comedy videos on YouTube, such as shaky camera motion or audible laughter, which we can automatically detect. While content-based features worked well for music, identifying humor based on just such features is AI-Complete. Humor preference is subjective, perhaps even more so than musical taste.
- . . . 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. To this end we computed more text features based on words associated with amusement in comments. These included (a) sounds associated with laughter such as hahaha, with culture-dependent variants such as hehehe, jajaja, kekeke, (b) web acronyms such as lol, lmao, rofl, (c) funny and synonyms of funny, and (d) emoticons such as :), ;-), xP. We then trained classifiers to identify funny videos and then tell us why they are funny by categorizing them into genres such as “funny pets”, “spoofs or parodies”, “standup”, “pranks”, and “funny commercials”.
- Next we needed an algorithm to rank these funny videos by comedic potential, e.g. is “Charlie bit my finger” funnier than “David after dentist”? Raw viewcount on its own is insufficient as a ranking metric since it is biased by video age and exposure. 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? We designed features to quantify the degree of emphasis on words associated with amusement in viewer comments.
The top results were voted on by the public, and here’s what came in first place (see below).
Underwhelming, right? I don’t know about you, but I really, really wanted to laugh–I was making a good-faith effort at being amused—but there was nothing. No giggles. No snicker. Not even a smile. And, for the record, I have a very low comedy bar, meaning that it doesn’t take much to make me laugh. So if this is the funniest video on the web–if this is what human humor is defined as by our programmers—then I am, in the immortal words of Downton Abbey‘s O’Brien, a banana.