If you’ve ever gotten a little too deep into Netflix, you’re probably more than familiar with the bizarrely specific categories that tend to show up in your recommendations. I’ve never understood why the service recommends things like “Foreign Films With Mediorce Lip Dubs” and “British Comedies Featuring People With Bad Teeth,” but thanks to Tech Radar, I finally have an answer.
It turns out those long-winded suggestions are mostly the handiwork of Mike Hastings, who reviewed movies before deciding to dedicate his skills to a nobler cause by leading a 30-person team of people who get paid to spend their day watching movies and television shows and tagging each piece of content with up to 250 tags.
It might sound like a dream job, but when you realize someone has to suffer through all of the Netflix exclusives Adam Sandler got paid way too much money to make and the last three seasons of Dexter, it seems slightly less appealing. While Hastings stressed the importance of the human element, he also said the long-winded descriptions you come across are also the product if the almighty algorithm:
Hastings and his team set up “tester accounts” that are given different personalities, and so are exposed to different combinations of tags. “We’ll have one that’s in to one type of content, one that’s into another type of content, and we’ll see both our rows and our algorithmic rows, are they making sense, are they doing anything that’s strange?”
Once the algorithms are let loose in the wild, the team’s work continues with them monitoring social media for any mentions of odd combinations of tags. “We watch Twitter for screenshots of recommendations that people think are wrong or bad.”
I can’t say I’ve ever actually watched any of the movies and TV shows that have ended up under the umbrella of the eight-word categories that have shown up in my recommendations, but based on the sheer amount of enjoyment I’ve gotten out of encountering seemingly random lumps of words doing everything they can to suck me into a black hole of suggestions, I’d like to thank Hastings for his service.