Email or username:

Password:

Forgot your password?
Siderea, Sibylla Bostoniensis's posts Post Back to profile
Siderea, Sibylla Bostoniensis

I've noticed a thing about the YouTube recommendation algorithm.

I had heard about the new Beyoncé single Texas Hold 'Em, so I searched for it on YouTube so I can listen to it. Subsequently, it started proposing to me various dance videos that people had made to that song. Perfectly reasonable. I watched several of those too. Then I got bored and wandered off.

After that, I noticed that the YouTube algorithm was absolutely convinced I wanted to see completely random videos that happened to use Beyoncé's Texas Hold 'Em as background music.

Which, yes, is the way that machine learning often fails: it gloms on to some detail, fails to note any sort of context bc it doesn't *do* context, and concludes that's the relevant detail to optimize for.

It was a pretty striking example, and suddenly I realized: this is not the first time. Until this happened, I hadn't noticed, but YouTube's recommendation algorithm will often show me video after video with the same *background music*.

11 March at 9:29 | Open on universeodon.com
2 comments
Siderea, Sibylla Bostoniensis

For instance, I noticed a while back that umpteen zillion random shorts wound up in my feed that all had Jain's Makeba as the soundtrack. I had just thought it was wildly popular, because it is indeed a super catchy bop.

In retrospect I think maybe what happened was that the YouTube algorithm noticed I – entirely coincidentally – watched all the way through two random videos which happened to use the same soundtrack, and concluded what I like to see is videos that use that song.

Same thing happened with Paris Paloma's Labour. And the Longest Johns' Wellerman. And some group of basses singing Hoist the Colors (which, delightfully appropriately, resulted in a stream full of 100% unadulterated thalassophobic naval architecture porn.)

For instance, I noticed a while back that umpteen zillion random shorts wound up in my feed that all had Jain's Makeba as the soundtrack. I had just thought it was wildly popular, because it is indeed a super catchy bop.

In retrospect I think maybe what happened was that the YouTube algorithm noticed I – entirely coincidentally – watched all the way through two random videos which happened to use the same soundtrack, and concluded what I like to see is videos that use that song.

11 March at 9:35 | Open on universeodon.com
Siderea, Sibylla Bostoniensis

Meanwhile, it doesn't matter how much early music I listen to, it almost never recommends me other early music. If I listen to one early music artist enough, it might recommend other videos by the same recording artist. But I can listen to 10 different versions of, say, Belle Qui Tient Ma Vie, and it will *never* recommend me another one.

This is actually a reasonably common occurrence: if I'm going to link to a recording of an early music piece in something I'm writing, I will go and listen to absolutely every version I can find on YouTube till I find the one I find optimal or run out of spoons. So when I linked to "A Virgen mui groriosa" (Cantiga de Santa Maria number 42), I listened to *every single one* I could find on YouTube. And at no point did the YouTube recommendation algorithm cotton on to the fact that I was actually interested in that.

It did throw up a couple other Cantigas, in a fitful effort, but when I didn't bite, it stopped.

Meanwhile, it doesn't matter how much early music I listen to, it almost never recommends me other early music. If I listen to one early music artist enough, it might recommend other videos by the same recording artist. But I can listen to 10 different versions of, say, Belle Qui Tient Ma Vie, and it will *never* recommend me another one.

11 March at 9:50 | Open on universeodon.com
Go Up