TikTokJump to a section
What are recommender systems? • How our recommender systems work • How content is recommended across TikTok • How you can influence what is recommended to you • How you can manage personalization on TikTok
What are recommender systems?
TikTok's mission is to inspire creativity and bring joy. We have a wide variety of content and creators to discover, so you can find what's most interesting and relevant to you. That's why we use recommender systems to offer you a personalized experience. These systems suggest content based on your preferences, which are informed by your interactions, such as following an account or liking a post on TikTok.
How our recommender systems work
Understanding signals
When you first sign up for TikTok, we may invite you to select categories of interest, like pets or travel, which help us form your For You, Explore, and LIVE feeds. If you skip this step, we start by showing you recent posts that are popular with others on TikTok.
When selecting your initial set of posts, we look for and suggest:
• Popular content appropriate for a broad audience.
• Content influenced by your location and language settings.
In addition, we'll suggest popular creators for you to follow.
Once you start interacting on the app, your interactions act as signals that help the recommender systems 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. Your interactions across TikTok can impact how the system ranks and serves you content. Keep in mind that if you opt not to follow any creators or you don't have any friends on TikTok, then you might not see content in your Friends Tab or Following feed.
Selecting and ranking content
We recommend content based on several factors to predict how relevant and interesting content might be to a user. The main factors are:
• User interactions
• Content information
• User information
A few things to know about ranking:
• Each of these factors can play a larger or smaller role in what's recommended and how content is ranked. How important each factor is can change over time.
• The factors that play a larger role do the best job of showing us the types of content you might enjoy.
Each recommender system selects from a large collection of eligible content and ranks them based on the system's prediction of how likely you'll be interested in each one. In certain recommender systems, these predictions also consider interactions from others who appear to have similar interests. For example:
• If User A likes videos 1, 2, and 3;
• User B likes videos 1, 2, 3, 4, and 5;
• then the recommender system may predict User A will also like videos 4 and 5.
Since everyone has different preferences and signals, recommendation feeds like For You, Following, Friends, and LIVE remain unique to each person, even if some occasionally see the same content.
Diversifying recommendations
Our goal is to show you relevant content while also helping you discover new interests. We aim to diversify your feeds by introducing you to new creators and content so you can explore different perspectives and ideas. That's why you may come across content in your For You and LIVE feeds that doesn't appear to be relevant to your expressed interests. We also typically don't recommend content you've already seen.
Similarly, with your Friends Tab and Following feed, you may see multiple posts from the same creator, but we generally won't recommend two posts in a row from that creator. If you follow only them, then we may recommend multiple posts in a row. If you run out of content to watch on your Friends Tab or Following feed, then we'll suggest that you explore content on your For You feed.
Safeguarding your experience
Our recommender systems are designed with safety as a key consideration, and we remove any content identified as violating our Community Guidelines. We do not recommend in the For You feed content that, while permitted on TikTok, does not meet our For You feed eligibility standards.
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.
We continually review LIVE videos to interrupt and stop LIVE content that violates our Community Guidelines. We may also restrict creators from going LIVE who violate these guidelines. People under the age of 18 are not permitted to host a LIVE or to send Gifts, and are restricted from watching certain LIVE videos.
Our safety teams may review certain content as it rises in popularity to help ensure it's suitable for everyone.
Our For You feed rules aim to interrupt frequent recommendations of certain content that may be fine when seen occasionally, but could lead to a negative experience if seen repeatedly, such as extreme fitness or dieting.
Learn more about our FYF eligibility standards in our Community Guidelines.
How content is recommended across TikTok
You can view content through several feeds and features, which we continually improve and expand over time. Here are some popular examples:
In your feeds
For You
The For You feed displays a stream of content just for you, so you can find content and creators you love.
Here are some examples of what may influence the content in your For You feed:
• User interactions: Content you like, share, comment on, and watch in full or skip, as well as accounts of followers that you follow back.
• Content information: Sounds, hashtags, number of video views, and the country in which the content was published.
• User information: Device settings, language preference, location, time zone and day, and device type.
For most users, user interactions, which may include the time spent watching a video, are generally weighted more heavily than others.
Following
The Following feed displays content from creators you follow. Each Following feed is unique—even if two people follow the same creators, their feeds will rank and serve content in a way that's tailored to how they use TikTok.
Here are some examples of what can influence the content in your Following Feed: • User interactions: Visits to the user profiles you follow and the content you like, share, comment on, and watch in full or skip.
• Content information: Sounds, hashtags, number of video views, and the country in which the content was published.
• User information: Device settings, language preference, location, time zone and day, and device type.
For most users, user interactions, which may include the time spent watching a video, are generally weighted more heavily than others.
Friends
The Friends Tab displays content from followers you follow back (your friends), accounts you follow, and other suggested accounts. Even if two people follow the same creators, their Friends Tab will rank and serve content in a way that is unique to each of them.
Here are some examples of what can influence the content in your Friends Tab:
• User interactions: Visits to the profiles of your friends or people you may know and the content you like, share, comment on, and watch in full or skip.
• Content information: Sounds, hashtags, number of video views, and the country in which the content was published.
• User information: Device settings, contacts (with your permission), language preference, location, time zone and day, and device type.
For most users, user interactions, which may include the number of likes and comments on a video, are generally weighted more heavily than others.
LIVE
The LIVE feed displays a stream of LIVE videos that allows you to find content and creators you love. You can view LIVE videos by selecting the LIVE button at the top of the For You feed, or you may see recommended LIVE videos in your For You feed.
Here are some examples of what may influence the content in your LIVE feed:
• User interactions: LIVE videos you like and comment on, creators you follow, watch time, and Gifts sent.
• Content information: Hashtags, number of LIVE views, number of likes, number of Gifts sent during the LIVE, number of followers of that creator, and the country in which the LIVE is taking place.
• User information: Device settings, language preference, location, time zone and day, and device type.
For most users, user interactions, which may include the time spent watching a specific LIVE, are generally weighted more heavily than others.
E-commerce
TikTok Shop
TikTok Shop provides products to browse and purchase through content, such as posts with product links. You can view TikTok Shop content and products through your TikTok feeds, search feature, or Shop Tab where available. Learn more about how content is recommended on TikTok Shop.
Discovery
Search
Our search features allow you to search for content on TikTok. They also recommend search terms for you to discover content.
Here are some examples of what may influence the content in your recommended search terms and search results:
• User interactions: Your past search behavior and the content you like, share, comment on, and watch in full or skip.
• Content information: How well the content matches your search inquiry, hashtags, and the sound used.
• User information: Device settings, language preference, and location.
For most users, content information, which may include how well the content matches the specific term entered, is generally weighted more heavily than others.
Notifications
We'll send you notifications to recommend content you might like, people you might know, or search terms you might be interested in.
Here are some examples of what may influence the notifications we send you:
• User interactions: How active you've been on TikTok and your previous interactions with notifications.
• Content information: Creator of the content, hashtags, number of views, and the country in which the content was published.
• User information: Your location, language preference, and device type.
For most users, user interactions, which may include the number of notifications you receive and open, are generally weighted more heavily than other factors.
Interactions
Comments
We recommend comments on posts we think you'll be interested in to help build connections within the TikTok community.
Here are some examples of what may influence the comments we show you:
• User interactions: Comments you like, reply to, and if you follow the creator of the post or author of the comment.
• Content information: Number of likes and the language of the comment.
• User information: Your location and language preference, and device settings.
For most users, content information, which may include the language of the comment and how many likes it receives, is generally weighted more heavily than others.
Account recommendations
On TikTok, you can connect with people you may know and creators who might interest you based on who you're already engaging with.
Here are some examples of what may influence account recommendations:
• User interactions: Your activity on TikTok, such as the types of accounts you follow, like, or share content with.
• Content information: Number of followers and views an account has, account location, and the likelihood that you know another account, for example, if they're in your contacts (with your permission).
• User information: Device settings, language preference, and location.
For most users, content information, which may include the number of mutual connections between two accounts, is generally weighted more heavily than other factors.
How you can influence what is recommended to you
While we've shared that there are many reasons why content is recommended to you on TikTok, there are several ways you can influence this content. We provide the following features and settings to support this:
• Like: Liking content helps TikTok suggest similar content in the future.
• Not interested: If you don't enjoy a specific piece of content in your feeds, you can let us know by sharing feedback that you're not interested, and we'll show you less content like that.
• Refresh your feed: You can update the content we recommend on your For You feed and interact with popular content, such as liking and commenting, to help reshape your For You feed recommendations.
• Manage topics: You can adjust your preferences for different topics to customize the content on your For You feed.
• Dislike for Comments: Let us know if you're not interested in a comment by disliking it within the comments section of a post.
In addition, TikTok offers a number of other features you can use to customize what you see:
Customizing feeds
Customize your feeds with these tools:
• Filter keywords: You can use filters to remove content containing specific words and their variations, and hashtags from your For You, Following, Friends, LIVE, and STEM feeds. After adding a keyword to Filter Keywords, users can choose to use AI to filter out similar keywords, like synonyms, and their variations.
• Unfollow: Unfollowing an account can remove their posts from your Following feed or Friends Tab.
Customizing search results
Customize your shopping and search experience with these tools:
• Filters: You can choose to filter the search results to refine your search. For example, on the Shop Tab, you can filter by price range, rating, color, or size.
• Sort by: You can sort your search results by relevance, likes, or date posted. If you're browsing on the Shop Tab, refine your search using best match, bestsellers, price (low to high or high to low), or newest items.
Customizing account recommendations
• Unsync your contacts: If you want TikTok to remove previously synced contacts or turn off synced contacts in your privacy settings.
• Remove suggested accounts: When we recommend accounts for you to follow, you can remove them from the suggested list to let us know you're not interested.
Customizing notifications
Manage notifications in your settings to choose what type of notifications you'd like to receive for suggested posts. Turn all notifications off or choose which interactions you'd like to receive notifications for.
How you can manage personalization on TikTok
The content you see and other features you use on TikTok, including TikTok Shop, are tailored to you based on your personal preferences or interests, giving you a personalized experience. Two types of personalization settings on TikTok are: personalized feeds and personalized search. Both settings are turned on by default, but you can turn them off by following these instructions.
• Turning off the personalized feeds setting will show you non-personalized content in the For You, Following, LIVE, and STEM (in select regions) feeds, Explore Tab, Friends Tab, Nearby Tab (in select regions), and Shop Tab (in select regions). For example, your Following and Friends feeds may feature content from creators you follow in chronological order. The For You feed will become a Popular feed and serve popular content from your region and internationally. Comments, Stories, and account recommendations are also not personalized when this setting is turned off.
• Turning off the personalized search setting will show you non-personalized search results and recommendations. This will also change suggested search queries and how search results are ranked.
Learn more about how to manage personalization on TikTok.
Note: This non-personalization feature is only available in the EU and Kazahkstan.