Although TikTok’s algorithm appears to be complicated and enigmatic, the company has revealed how it actually works. The algorithm is influenced by a variety of factors and includes: hashtags used, location, music preferences, and even the first TikTok video you ever liked.
As someone who has recently joined TikTok, I was intrigued to look into how the algorithm started to shape itself around my interests. So, here’s what I learned so far.
In a press release last year, TikTok detailed how the #ForYou stream is calibrated and tailored for each user. Previously, we could only presume that the For You page was a curated feed that pulled content from your profile, location, and similar videos you’d already liked and engaged with.
But, according to the press release by TikTok:
“When you open TikTok and land in your For You feed, you’re presented with a stream of videos curated to your interests, making it easy to find content and creators you love. This feed is powered by a recommendation system that delivers content to each user that is likely to be of interest to that particular user. Part of the magic of TikTok is that there’s no one For You feed – while different people may come upon some of the same standout videos, each person’s feed is unique and tailored to that specific individual.
The For You feed is one of the defining features of the TikTok platform, but we know there are questions about how recommendations are delivered to your feed. In this post we’ll explain the recommendation system behind the For You feed, discuss how we work to counter some of the issues that all recommendation services can grapple with, and share tips for how you can personalize your discovery experience on TikTok.”
Basically, “the system recommends material by ranking videos based on a variety of factors,” according to TikTok, “starting with interests you express as a new user and adjusting for items you indicate you’re not interested in, as well.”
Indicators of interest
Here are some of the ways the TikTok app tailors its content:
- User activities such as the videos you like or share, the accounts you follow, the comments you make, and the content you generate, are all examples of these characteristics.
- Information about the video, such as captions, audio, and hashtags.
- Language preference, country setting, and device type are examples of device and account settings.
TikTok’s For You suggestion system weighs each of these elements independently, making each For You page uniquely tailored to the person and their degree of interest. TikTok, for example, indicates that a user’s completion of a movie from beginning to end could be a strong indicator of interest. This would be given more weight than a flimsy signal like whether the video’s producer and viewer are from the same country. The For You page videos are then ordered depending on the likelihood of a user’s interest in a piece of material using these “indicators of interest.”
While this is only a preliminary understanding of the algorithm, made for the purpose of understanding how it works, it can also help you understand how you can influence it to your advantage and interests.
For those who are interested in more TikTok news, TikTok has also recently begun testing a disappearing stories feature.