A blog post written by Instagram CEO Adam Mosseri explains how Instagram actually works.

In the post, he wants to answer questions like: “How does Instagram decide what shows up for me first?”; “Why do some of my posts get more views than others?”; and “How does Instagram decide what to show me in Explore?”

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

Algorithms of Instagram:

According to Mosseri Instagram doesn’t have one algorithm that oversees what people do and don’t see on the app. Instead, it uses a variety of algorithms, classifiers, and processes, each with its own purpose.

Instagram creates Feed that ranked posts based on what you users about most.

Each part of the app – Feed, Explore, Reels – uses its own algorithm tailored to how people use it. People tend to look for their closest friends in Stories, but they want to discover something entirely new in Explore. It ranks things differently in different parts of the app, based on how people use them. These are called signals.

Ranking of Feed:

Vast majority of post in feed is shared by people followed by a user.

Taking all information about post, people who posted it and user’s preferences. These are called ‘signals’ and there are thousands of them. They include everything from what time a post was shared to whether users are using a phone or the web to how often users like videos. The most important signals across Feed and Stories, roughly in order of importance, are:

  • Information about the post. These are signals both about how popular a post is numbers of likes, and more mundane information about the content itself, like when it was posted, how long it is if it’s a video, and what location, if any, was attached to it.
  • Information about the person who posted. This helps us get a sense of how interesting the person might be to you, and includes signals like how many times people have interacted with that person in the past few weeks.
  • User Activity. Helps in understanding user’s interests and includes signals such as how many posts a user has liked.
  • User’s history of interaction with the content creator. This gives us a sense of how interested a user is generally in seeing posts from a particular person. An example is whether or not users comment 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

Safety and Community Guidelines:

  • If a post harms the safety of other users, the algorithm takes it down.
  • Violations of Instagram’s community guidelines user’s videos may get taken down, and frequent violations may result in account suspension.
  • Posts identified as misinformation gets labeled, and get lower in feed, if someone spreads frequent misinformation through posts, the algorithm makes it harder to find.

Ranking of Explore

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 recommendations guidelines that’s unique to content recommendations. These include things like avoiding potentially upsetting or sensitive posts, for example, Instagram aims to not show content that promotes tobacco or vaping use in Explore. 

In the post, Mosseri also explains what Instagram uses to rank posts on the Explore page and in the Reels section. To better influence the algorithms, here are a few tips:

  • Pick your Close Friends;
  • Mute people you’re not interested in;
  • Mark recommended posts as “Not Interested.”

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