The TikTok secret algorithm is a big ‘Duh!’


TikTok’s powerful algorithm that controls the social media activities of millions of daily users is no longer a secret.

In a new one New York Times report that outlines information extracted from a document verified as an official document, TikTok’s algorithm is disclosed. Wait: it prioritizes retention and time spent, and it’s insanely obvious.

Stripped down to the basics, the TikTok algorithm looks for video likes, comments, and how much of the video you’re watching (a fully viewed video is obviously worth more than one you stop at or scroll past before it’s done is).

The system uses tags and other details to understand what each video is about. If you like a certain type of video and you see through it completely, or even pause several times and then play it back to the end, these are positive signals for the algorithm.

Since TikTok’s goal is to get you back to the platform as often as possible and keep your attention once you’re there, the algorithm will then feed you through TikTok with more of the kind of videos you indicated you were like / prefer algorithm

It’s an addicting virtuous cycle, isn’t it?

Videos stringing together a story – and getting you to see them all – can increase this subject’s influence on the algorithm to give you more of that type of meaty content.

A path to content addiction

When I started watching TikTok videos a few years ago, practically all of them were 15 seconds or less long. My feed was full of magic tricks, DIY, and people performing dances. None of this, even then, was accidental. I was interested in learning new magic tricks (I’ve been an amateur magician for most of my life), I love home hacks and couldn’t get enough of the dances because I appreciated the skills and wondered how people of all ages (including mine!) had the ability and energy to learn and do them. What I was watching fed all of the videos I saw. To this day, my youngest child often says that I see a very different TikTok than they do.

Nowadays I watch longer storytelling videos, like the one from Elise Meyers, which I stumbled upon a few months ago when she was telling this long and hilarious story about a blind date who picked her up, drove to Taco Bell and then bought 100 tacos.

She is a brilliant storyteller. I know this because I’ve now consumed dozens of their videos thanks to the algorithm that is feeding me more and more of it (along with other long storytelling videos).

Those three-minute TikToks are obviously a boon to TikTok’s core goal of collecting and retaining more users. The time spent as a metric isn’t just reserved for TikTok. Anyone who runs a content website knows how much more time (and more pages) it takes, which usually results in more ads being served.

Down the rabbit hole

What’s noteworthy, however, is that TikTok’s algorithm still enables discovery. Yes, there are many out there who will show you more of what you clearly like or want (to the possible detriment of those who may be in a dark place and drawn to depressing / angry / harmful videos).

On the other hand, TikTok keeps a bit of luck. Every now and then I see a video that has nothing to do with my preferences or interests (at least as I put it on TikTok), but I get addicted. This is what happened to Elise Meyers. These random videos are usually a product of extreme popularity elsewhere on TikTok, which then inserts this content into your feed so you can feed the algorithm with new attention information.

The downside to this fairly simple algorithm is that it appears to get stuck. All of a sudden I have five or six Elise Meyers in a feed session, and even I can’t work through that many minutes of their crazy stories. I usually take a break and then come back to them.

I also found that once you understand the TikTok algorithm, you can train and retrain it. When I find too much of any type of video in my feed. I do a few hashtag searches and then some new topics.

This usually works until I go back to my old favorite spots (Magie, DIY, FX, Elise Meyers) – and then I’m back to where I started.


Comments are closed.