Instagram on How Its Algorithms Work

A blog post written by Instagram CEO Adam Mosseri explains how content is ranked for users in different sections of the app.

Mosseri goes over how content is ranked in the main feed, the explore feed, the reels feed, and the stories carousel.

In addition, Mosseri touches on the topic of shadowbanning and whether peoples’ theories about it are true.

Here’s a summary of key highlights from Mosseri’s article.

The Instagram Algorithm(s)

There is no one algorithm that ranks all content on Instagram, Mosseri says.

Each part of the app — Feed, Explore, Reels, & Stories — has its own algorithm. Content is ranked in each of these sections based on how people use them.

How The Feed & Stories Algorithms Work

The Feed and Stories algorithms rank recent posts shared by people a user follows.

Thousands of signals are used to determine the order in which to display the content.

Mosseri says these are the most important signals across the main feed and stories carousel:

• Information about the post: This includes how popular it is, how many likes it has, when it was posted, where it was posted from, and other general details.
• Information about the content creator: This includes how much engagement the creator has received in the past few weeks.
• User activity: Includes signals from the user’s recent activity on Instagram, such as how many posts they’ve liked.
• A user’s history of interacting with the content creator: An example is whether the user and the content creator have commented on each other’s posts.

From there, the algorithms try to predict how likely a user is to interact with a post.

The more likely a user is to take a engage with a post, the higher the post will rank.

For feed posts, Instagram looks at how likely a user is to:

• Spend a few seconds on a post
• Comment on a post
• Like a post
• Save a post
• Tap on the profile photo associated with the post

There are some cases where the algorithm takes other factors into consideration. For example, the Instagram feed will avoid showing too many posts in a row from the same person.

How the Instagram Explore Algorithm Works

The Instagram Explore algorithm ranks content in a separate feed from accounts that a user doesn’t already follow.

It works in a similar way to the main feed algorithm by gathering signals from posts a user has liked, saved, or commented on in the past.

Mosseri explains how those signals are used to find relevant content from accounts that a user isn’t directly connected with:

“Let’s say you’ve recently liked a number of photos from San Francisco’s dumpling chef Cathay Bi (@dumplingclubsf). We then look at who else likes Cathay’s photos, and then what other accounts those people are interested in. Maybe people who like Cathay are also into the SF dim sum spot @dragonbeaux. In that case, the next time you open Explore, we might show you a photo or video from @dragonbeaux. In practice, this means that if you’re interested in dumplings you might see posts about related topics, like gyoza and dim sum, without us necessarily understanding what each post is about.”

After the Instagram Explore algorithm finds posts a user may be interested in, it ranks them using the same signals as the main feed.

To recap, those signals are:

• Information about the post
• A user’s activity on Instagram
• A user’s history of interacting with the content creator
• Information about the content creator.

Lastly, content selected for the Explore feed has to clear a set of guidelines that’s unique to content recommendations.

This ends up in cases where content that’s otherwise suitable for Instagram may not be considered suitable for the Explore feed.

More Information About Instagram’s Algorithms

For more information on these algorithms, and details about the Reels algorithm, see Mosseri’s full blog post.

He also tiptoes around the subject of shadowbanning and veers the topic toward why content gets removed, rather than discussing why users see sudden drops in content visibility.