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.