Many have raised questions around TikTok’s "For You" feed that delivers recommended content to one’s feed. Additionally, "For You" is also one of the defining features of the TikTok platform, and presents a stream of videos curated to interests. In a blog post, the ByteDance-owned app breaks down the recommendation system behind the "For You" feed, and discusses how the company counters some of the issues that all recommendation services can grapple with, among others.
Recommendation systems are utilised by every social media platform, and powers many of the services an individual uses on a daily basis such as shopping, streaming and search engines. In general, these systems suggest content after taking into account user preferences as expressed through interactions with the app, such as posting a comment or following an account. These signals help the recommendation system gauge the content the user likes as well as the content they would prefer to skip. The system recommends content by ranking videos based on a combination of factors – starting from interests the user expresses as a new user and adjusting for things the user indicates as not interested in, too – to form the personalised For You feed.
Recommendations are based on a number of factors, including things such as:
- User interactions such as the videos you like or share, accounts you follow, comments you post, and content you create.
- Video information, which might include details like captions, sounds, and hashtags.
- Device and account settings like your language preference, country setting, and device type.
These factors are included to make sure the system is optimised for performance, but they receive lower weight in the recommendation system relative to other data points we measure since users don't actively express these as preferences.The factors are processed by its recommendation system and weighted based on their value to a user. A strong indicator of interest, such as whether a user finishes watching a longer video from beginning to end, would receive greater weight than a weak indicator, such as whether the video's viewer and creator are both in the same country. Videos are then ranked to determine the likelihood of a user's interest in a piece of content, and delivered to each unique For You feed.
“While a video is likely to receive more views if posted by an account that has more followers, by virtue of that account having built up a larger follower base, neither follower count nor whether the account has had previous high-performing videos are direct factors in the recommendation system,” it added.
Diversity is essential to maintaining a thriving global community, and it brings the many corners of TikTok closer together. To that end, TikTok added that users may come across a video in their feed that does not appear to be relevant to their expressed interests or have amassed a huge number of likes. This is an important and intentional component of TikTok's approach to recommendation: bringing a diversity of videos into one's For You feed gives users additional opportunities to stumble upon new content categories, discover new creators, and experience new perspectives and ideas.
"By offering different videos from time to time, the system is also able to get a better sense of what's popular among a wider range of audiences to help provide other TikTok users a great experience, too. Our goal is to find balance between suggesting content that's relevant to you while also helping you find content and creators that encourage you to explore experiences you might not otherwise see," the statement read.
The blog post comes shortly after TikTok addressed the recent zero view count display around hashtags #BlackLivesMatter and #GeorgeFloyd. On 28 May, TikTok said its systems encountered an issue that caused significant delays in data consumption. While this delay was ongoing, a user who was considering adding a hashtag to a post they were composing would be shown a view count result of zero views, even if there were billions of views.
“This display issue - which impacted a total of 225,611 unique hashtags, but could have impacted any searched hashtag - was due to inefficiencies in our data stream flushing service design,” head of user and product operations Seth Melnick and senior back-end engineer Somar Musa added in the post. Both Melnick and Musa explained that hashtags #georgefloyd and #blacklivesmatter were showing zero views as users were preparing their post before uploading, and that this was due to a lag in data-stream. The engineering team has since ran tests and tweaked its processor to ensure the hashtag counts will not be disrupted.
Share your thoughts with us journos in the newsroom and be part of our Instagram community to catch the behind the scenes action, industry updates and creative inspiration!
TikTok hunts for APAC agency development lead
Former OMD Indonesia GM Rahul Divay heads to TikTok
TikTok appoints agency partner for branded content, looks to grow team
TikTok names head of communications for SEA markets
Analysis: TikTok queries spike for content creators, but will the dollars trickle in too?