Among the ongoing cavalcade of legislators and laity concerned about whether the social media algorithms might be rotting the brains of its users, TikTok has faced a great deal of scrutiny, and for good reason. Despite the application use of balloons around the world, with balloons income figures To match, there is still a lot we don’t know about how the company hooks its users and keeps them coming back for more.
Northoh, thanks to a new report from Ben Smith’s New York Times reportWe finally got a look.
The Times did not share a copy of the document, allegedly titled “TikTok Algo 101,” in its report, and Gizmodo was unable to track down a copy to confirm the details for ourselves. That said, a TikTok spokesperson confirmed the document.authenticity, saying it was meant to explain to less tech-savvy employees how the platform’s algorithms work. The Times explains that it was one of those employees who in fact, he leaked that document to the newspaper, noting that they were “upset” by the platform’s tendency to push users towards “sad” content that could depress users.
The Times’ description of the document does not refer to any of the disturbing content that may arise among its users. feeds. But does it talk a little math. That is because, at the end of the day, no the algorithm is composed of arcane fragments of black magic, like some lawmakers could involve. Instead, these algorithms (any algorithm, really), are designed to convert their behavior on the platform into a series of figures and use those figures to inform what content should be in your feed.
The real question is where those numbers come from. A recent report of tThe Wall Street Journal, for example, found that TikTok’s recommendation systems are highly dependent on the time you spend watching a given video.
Other third-party analyzes have repeated These findings, which point to following a given clip to the end (or even better yet, rewatching it multiple times), will almost certainly result in TikTok serving you more of that type of content.
But according to the document the Times reviewed, looking (or looking again) at time is not the only ingredient used by the TikTok algorithm. In addition to those figures, the algorithm also takes into account other numbers: the number of likes and comments a video has, how long that video is (its “watch time”), and whether that video was played by a user. There’s even a useful equation for math nerds:
Plike X Vlike + Pcomment X Vcomment + Eplaytime X Vplaytime + Pplay X Vplay
“The recommendation system scores all videos based on this equation and returns the videos with the highest scores to users,” the document says. “For the sake of brevity, the equation shown in this document is greatly simplified. The actual equation in use is much more complicated, but the logic behind [it] is the same.”
As for what this algorithm is ultimately designed for, you might not be surprised that TikTok, like every other main social platform: pursue growth. The Times said that the document describes “frankly” that the “” ultimate goal “of the company [is] add daily active users ”, which is why the platform is optimized for content that keeps users coming back and keeps coming back for longer. blacksmith writes:
[The algorithm] you’ve chosen to optimize for two closely related metrics in how streaming videos you post: “retention,” meaning whether a user returns, and “time spent.” The application wants to keep you there as long as possible. The experience is sometimes described as an addiction, although it is also reminiscent of a frequent criticism of pop culture.
In that sense, the Times is right. Before the people were (rightfully!) concerned about social media addiction, critics in the 90s They were worried on TV viewers getting addicted to their gadgets and critics in the ’80s (and beyond) They were worried about video game addiction. And like today’s social media platforms, those technologies were built to keep users watching, playing games, and generally spending more. hour in front of a screen. More time spent tv broadcast Y playing games means more money in the pockets of the streaming and gaming giants behind those forms of media, in the same way that more time spent on TikTok means more money for TikTok.
“While the models can be complex, there is nothing inherently sinister or incomprehensible about the TikTok recommendation algorithm outlined in the paper,” Smith. writes. That doesn’t mean we should stop worrying about the influence of TikTok in general, there are many reasons that the company has already aroused the amazement of technology critics. But it serves as a good reminder to stop treating algorithms as an arcane, indescribable horror that lurks within our applications, and more for what they are: mathematical models designed to take our behavior online. and turn it into offline earnings.