The suprisingly familiar character of the TikTok algorithm

After a few weeks of using TikTok I was convinced the platform was radically different from services like Facebook and Twitter. The speed with which the stream was (successfully) personalised stunned me and the relatively peripheral character of follower counts left me convinced this didn’t involve what Jose Van Dijck calls the popularity principle. However as the Protocol newsletter reported today it’s actually incredibly familiar:

This secret document is what ByteDance calls “TikTok Algo 101,” written by engineers in Beijing to explain to nontechnical TikTok employees how the app makes algorithmic recommendations.

The company’s “ultimate goal” is growing daily active users by increasing user retention rates and total time spent each time TikTok is opened.

Each video is scored by the number of likes, comments and playtime. There’s even a handy formula for success, according to the document: Plike X Vlike + Pcomment X Vcomment + Eplaytime X Vplaytime Pplay X Vplay.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.