The music industry knows that TikTok’s #ForYou personalised recommendations feed is hugely powerful in racking up views for the videos chosen by its algorithm. But we also know that we don’t really know how that algorithm works – and nor, frankly, does most of the TikTok community, although theories abound.
Now TikTok has offered some official information on that mysterious recommendation algorithm, and while it’s not dishing all its secrets out, the blog post is worth a read. It explains that For You ranks videos “starting from interests you express as a new user and adjusting for things you indicate you’re not interested in, too”.
How does it adjust? A blend of user interactions – likes, shares, follows, comments and the videos you create – and the information within videos like captions, sounds and hashtags, as well as language, country setting and device type. This is interesting though: “neither follower count nor whether the account has had previous high-performing videos are direct factors in the recommendation system”.
TikTok users with lots of followers do tend to get more views because they have more followers, but that doesn’t give them an advantage in appearing in the For You feed. There’s more detail on and around this in the post.
No comments:
Post a Comment