TikTok reveals details, and challenges, of its recommendation algorithm

Mariam Cheik-Hussein
By Mariam Cheik-Hussein | 19 June 2020
TikTok

TikTok has for the first time explained how its recommendation feed works, and addressed how it's facing the challenge of filter bubbles.

When users open the short-form video app, they’re met with the For You feed which plays an endless stream of videos curated to the user’s interests. The personalisation experience of this feed has been a strong point for TikTok.

In a blog post, the company explained that, as with many social media algorithms, TikTok ranks videos based on a combination of factors, starting with interests users express. It also takes into account a user’s interaction with videos, shares, comments, and accounts they follow and content they create.

The algorithm also looks at account information such as captions, sounds, hashtags, and, to a lesser extent, device and account settings, such as language preference, country setting and device type.

“All these factors are processed by our recommendation system and weighted based on their value to a user,” the post states.

“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.”

For safety, the algorithm suppresses reviewed content found to depict things such as “graphic medical procedures” or “legal consumption of regulated goods”.

While users with a large follower base will naturally have a wider reach, TikTok says a user’s follower count or previous video performances aren’t a direct factor in the recommendation system, which helps explain why new users can explode on the platform in a short amount of time.

The social media company also directly addressed the challenge of “filter bubbles” that algorithms often create. One way it’s trying to fight this is by breaking up videos it already knows a user enjoys with diverse content.

“For example, your For You feed generally won't show two videos in a row made with the same sound or by the same creator,” TikTok says.

“We also don't recommend duplicated content, content you've already seen before, or any content that's considered spam. However, you might be recommended a video that's been well received by other users who share similar interests.”

TikTok has previously come under fire for the lack of diversity on its platform, with it reportedly limiting the reach of some communities, such as disabled users. However, TikTok highlighted its commitment to showing diverse content to users even though they may not “appear to be relevant” or have “a huge number of likes”.

“This is an important and intentional component of our approach to recommendation: bringing a diversity of videos into your For You feed gives you additional opportunities to stumble upon new content categories, discover new creators, and experience new perspectives and ideas as you scroll through your feed,” the company says.

Have something to say on this? Share your views in the comments section below. Or if you have a news story or tip-off, drop us a line at adnews@yaffa.com.au

Sign up to the AdNews newsletter, like us on Facebook or follow us on Twitter for breaking stories and campaigns throughout the day.

comments powered by Disqus