top of page

The TikTok Algorithm, Explained

Dan Flay takes look at the factors influencing the TikTok algorithm and explains how it works.

© TikTok


In case you've been living under a rock these last few months (who could blame you), TikTok is the destination for short-form viral videos and has amassed over 3.7m active users in the UK alone. It is the 7th most popular social media platform in the world, with users spending an average of 41 minutes per day creating, watching and sharing videos.


But one mystery that has endured is TikTok's elusive algorithm until now. After spending hours shooting and editing a video, it's only natural for brands to want their content to be seen by as many people as possible. Up until recently though, TikTok's algorithm was a relative mystery, with creators learning on the go what would or wouldn't land them a coveted spot on the FYP (For You Page). In order for people to get the most out of the platform, TikTok decided to share a blog post detailing exactly how its algorithm works and how it determines what it predicts its users will like. This information has proven invaluable for brands looking to optimise their videos and maximise engagements.


Similarly to other social media platforms, TikTok feeds are built using a recommendation algorithm that personalises content for each user based on a number of factors and signals. Hashtags, comments, and music choices can all impact the TikTok algorithm and help it to gauge the types of content that users like as well as the content they'd prefer not to see.


Initially, TikTok feeds are created using a person's starting interests but as time goes on and the algorithm gets to know them better, the content that they see is increasingly tailored to their likes and dislikes. As a rule, recommendations are based on three main elements: user interactions, video information and device and account settings. TikTok explains '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'.


We've broken down each factor, below:


User Interactions

This spans everything from the content that a user likes, shares, and comments on to the accounts that they follow and the types of videos that they create and publish.


Video Information

TikTok gleans information from videos such as captions, sounds, and hashtags.


Device & Account Settings

Settings are only a small part of how the algorithm works (since users don't actively volunteer this information) but still have a role to play. They include language preferences, country settings, and device type.


Essentially, the way users interact on the platform affects their recommendations. If a user only follows fashion accounts, and routinely likes or comments on videos featuring clothing challenges or styling videos, TikTok will serve them with more of this type of content. It's also worth noting that certain indicators carry more weight than others. If a user watches a video from start to finish this will have a greater impact than a weak indicator, such as the location of the viewer in relation to the creator.


According to TikTok, 'neither follower count nor whether the account has had previous high-performing videos are direct factors in the recommendation system' when it comes to the FYP. If a video is posted by an account that has a large number of followers, it is not automatically guaranteed to perform well, although it does have the advantage of appearing in the the 'following' feed, a separate tab to the FYP at the top of the app. This notion is interesting because it signals that content is accessed by the algorithm on a case-by-case scenario and judged by relevance and quality rather than an account's perceived 'clout'. This is great news for brands looking to launch themselves on TikTok as they needn't worry about establishing a solid follower base on the platform before beginning to create and share.


There are a number of other ways that brands can use the TikTok algorithm to their advantage too, namely creating authentic, quality content that people will enjoy. Creators should centre their videos around trending topics, audio or challenges to help them connect with like-minded users. It's also important to retain viewership through engaging content that will encourage followers to watch until completion. Brands need to watch, learn and participate in order to build communities on this channel. Check out this post on how businesses are using TikTok for inspiration.


Words by Dan Flay

bottom of page