TikTokJump to a section
How recommendation systems work • How TikTok recommends content in For You • How to influence what you see on your For You feed • Other factors that influence how TikTok recommends content![]()
How recommendation systems work
TikTok's mission is to inspire creativity and bring joy. We have a wide variety of content and we want you to discover interesting and relevant videos. That’s why we use recommendation systems to offer you a personalized experience. These systems suggest content based on user preferences as expressed through interactions on our platform, such as following an account or liking a post. Your interactions act as signals that help the recommendation system predict content you're more likely to be interested in as well as the content you might be less interested in and may prefer to skip.
How TikTok recommends content in For You
When you open TikTok, you'll see the For You feed which displays a stream of videos just for you, so you can find content and creators you love. The For You feed's recommendation system selects videos from a large collection of eligible content and ranks them based on the system's prediction on how likely you’ll be interested in each video. This means everyone has a unique For You feed – while some may see the same videos, each user's For You feed is unique and tailored to that specific person.
When you sign up for TikTok, we may invite you to select categories of interest, like pets or travel, which help us form your feed. If you don't select any categories of interest, we start by offering you a feed of recent videos which are popular with others on TikTok. When selecting your initial set of videos, the recommendation system looks for popular videos that are appropriate for a broad audience and influenced by your country and language settings. Once you start engaging with content on TikTok, things like your views, skips, likes, comments, shares, and other interactions will shape your For You feed as the system begins to learn more about your preferences.
Recommendations in your For You feed are based on a number of factors, including:
• User interactions such as the videos you like, share, comment on, watch in full or skip, accounts you follow, accounts that follow you, and when you create content.
• Video information such as captions, sounds, hashtags, number of video views, and the country in which the video was published.
• User information such as your device and account settings, language preference, country, time zone and day, and device type.
We consider all these factors to predict how relevant and interesting content might be to a viewer. Different factors can play a larger or smaller role in what's recommended, and the importance—or weighting—of a factor can change dynamically. For instance, the time spent watching a specific video is generally weighted more heavily than other factors. However, if a viewer never finishes watching any videos, but watches a lot of videos posted by creators in the same region, then that region may have a relatively stronger weight compared to other factors for that viewer. Factors like device settings generally receive lower weight compared to other factors. These predictions are also influenced by the interactions of other people on TikTok who appear to have similar interests. For example, if User A likes videos 1, 2, and 3 and User B likes videos 1, 2, 3, 4 and 5, the recommendation system may predict User A will also like videos 4 and 5.
Learn more about why a specific video is recommended to you in our For You article.
How to influence what you see on your For You feed
Every new interaction helps the system learn about your interests and recommend content – so one of the best ways to influence your For You feed is to simply use and enjoy TikTok. The content you see on your For You feed should become more relevant the more you use TikTok.
You can also use the following features to help shape what you see on your For You feed:
• Not interested: If you don't care for a specific video, you can let us know by sharing feedback you're not interested and we'll show you fewer videos like it.
• Refresh your feed: If the recommendations on your For You feed don't feel relevant to you anymore, or you're looking for more variety in your feed, you can refresh your For You feed to view a new set of popular videos, as if you've just signed up for TikTok.
• Filter video keywords: Filter out specific words or hashtags from the content recommended to you in your For You and Following feeds.
Other factors that influence how TikTok recommends content
We designed the For You feed's recommendation system to continuously improve, correct, and learn from your engagement on TikTok, as well as to take other important considerations into account when recommending content for you.
Diversifying recommendations
At times you may come across a video in your For You feed that doesn't appear to be relevant to your expressed interests. This is because we aim to provide a diversity of content into your For You feed that gives you additional opportunities to discover new content categories, creators, and experience new perspectives and ideas. It also allows the recommendation system to get a better sense of what is popular among a wider range of audiences. Our goal is to find balance between suggesting content that's relevant to you while also allowing you to discover new and diverse content and creators.
Safeguarding your experience
Our recommendation system is designed with safety as a key consideration, and we remove content that has been identified as violating our Community Guidelines.
Our safety team takes additional precautions to review videos as they rise in popularity to reduce the likelihood of recommending content that may not be suitable for everyone on TikTok. For example, we strive to not recommend—or to limit the recommendation of—certain categories of content that may not be suitable for a general audience, even if that content is not removed from TikTok altogether. You can learn more about our content eligibility standards for the For You feed in our Community Guidelines.