Instagram has revealed how it recommends content to users in order to dispel “misconceptions” about how the app’s algorithm.
In a blog post published on Wednesday, Instagram CEO Adam Mosseri explains the app’s ranking system in detail.
“Instagram doesn’t have a singular algorithm that oversees what people do and don’t see on the app,” Mosseri explains in the post.
Instead, Mosseri says that there are multiple algorithms, classifiers, and ranking systems behind the various sections of Instagram which include Explore, Reels, Stories, and search.
For example, the order of posts in a user’s main feed is determined by their past activity on the app and whether they have had previous interactions with that person on Instagram.
Meanwhile, the stories in someone’s main feed are determined by how often that particular user views an Instagram account’s updates and whether they have had past interactions with the account such as liking a story or sending DMs.
Instagram will also attempt to understand a user’s relationship with an account, for example, whether they are likely connected as friends or family.
However, recommendations in Explore are predominantly based on posts a user has “liked, saved, shared and commented on in the past” — but are far more likely to arise from Instagram accounts that a user has never interacted with.
Reels recommendations use similar user data and can often come from an account that a user has not had past interaction with either.
In the post, Mosseri also discusses shadowbanning, which is a term used to describe when a user’s content is being hidden without a clear explanation or justification.
“Contrary to what you might have heard, it’s in our interest as a business to ensure that creators are able to reach their audiences and get discovered so they can continue to grow and thrive on Instagram,” Mosseri writes.
“If there is an audience that is interested in what you share, then the more effectively we help that audience see your content, the more they will use our platform.”
Mosseri says that Instagram users’ concerns about shadowbanning show that the app needs to increase transparency so people have more information about what is going on with their accounts.
Instagram isn’t quite making a habit out of explaining how its recommendations work, but it doesn’t seem to be keeping it a closely guarded secret either. Last year, the company published a detailed overview on how the app’s artificial intelligence (AI) selects suggested posts that users see in their feed, too.
Image credits: Header photo licensed via Depositphotos.