The company systematized the information according to where the user encountered the content. This could be the main feed, search, Stories, Explore page, and Reels – suggestions work differently for each item. “Instagram doesn’t have a single algorithm that controls what people do and see on the app”– explains Adam Mosseri, head of the company.

How does the Instagram algorithm work?

• Stories are partially ordered by how often a user views account updates and interacts with other users by sending personal messages or liking the story. Instagram also tries to gauge your relationship with the account, for example, whether it’s a family member or a friend.
• The order of posts in your main stream is also determined by your past activity and previous interactions with the person who made a particular post.
• Reels recommendations use similar user data: what you save, what you forward, what you like. It is also important whether you watch the video to the end – if so, its topic is interesting to you and you can offer more of the same. Also, the visual and sound effects used in the video is one of the criteria – if you click on a sound/effect, you may be interested in other videos with the same sound/effect.
• Suggestions in Discover are mostly based on “posts you’ve liked, saved, shared, and commented on in the past,” but they come from accounts you’ve never interacted with before.

One of the most interesting parts of the blog is “fighting shadow ban”. Mosseri notes that there is no universal definition of the term, but agrees that many creators “mean that a user’s account or content is restricted or hidden without explicit explanation or justification.” It also says the company is working to increase transparency about when content or author accounts are hidden from suggestions. Specifically, it points to an “account status” feature that can alert users when one of their posts or account is deemed “unsuitable” for referrals. This feature also offers an appeals process.

It is unknown whether Mosseri talked about all the intricacies of algorithms. Social networks have often been caught because they have hidden rules in their algorithms. Yes, Twitter was recently exposed for deliberately underestimating the publication of posts about the war in Ukraine.