Instagram recently announced that it will be shedding light on how its technology works and how it impacts people’s experiences.
First up, the Instagram algorithm.
Instagram doesn’t have one algorithm that manages what people do and don’t see on the app. In fact, it uses a variety of algorithms, classifiers, and processes to personalise your experience and make the most of your time on the app.
When it first launched in 2010, Instagram was a single stream of photos in chronological order. But as more people joined, it became impossible for people to see everything, least of all the posts they cared about. Five years ago, it was estimated that people were missing about 70% of all their posts in Feed, including almost 50% of posts from their close connections. This led to the development of a Feed that ranked posts based on what people care about most.
Each part of the app – Feed, Explore, Reels – uses its own Instagram algorithm tailored to how people use it. People tend to look for their closest friends in Stories, but they want to discover something new in Explore. So, the Instagram algorithm ranks things differently in different parts of the app, based on how people use them.
Feed and Stories ranked
Through the years, Instagram learned that Feed and Stories are places where people want to see content from their friends, family, and those closest to them. With any ranking algorithm, how it works can be broken down into steps.
First, Instagram defines the set of things it planned to rank in the first place. With Feed and Stories, this is relatively simple – all the recent posts shared by the people you follow. There are a few exceptions, like ads.
Next, it takes all the information it has about what was posted, the people who made those posts, and your preferences. These are called “signals”, and there are thousands of them. They include everything from when a post was shared to whether you’re using a phone or the web to how often you like videos. The most important signals across Feed and Stories, roughly in order of importance, are:
- Information about the post. These are signals include how popular a post is and more ordinary 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 Instagram 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 recent past.
- Your activity. Instagram wants to understand what you might be interested in and includes signals such as how many posts you’ve liked.
- Your history of interacting with someone. This gives Instagram a sense of how interested you are generally in seeing posts from a particular person.
Finally, Instagram makes a set of about 12 predictions that many consider to be the Instagram algorithm. These are educated guesses at how likely you are to interact with a post in different ways. In Feed, the five interactions with the highest considerations are how likely you are to spend a few seconds on a post, comment on it, like it, save it, and tap on the profile photo. The more likely you are to take any action, and the more heavily Instagram weighs that action, the higher up you’ll see the post. The Instagram algorithm has signals, and predictions added and removed all the time to get better at determining what you’re interested in.
There are a few cases where Instagram takes other considerations into account. For example, it tries to avoid showing too many posts from the same person in a row. Another is Stories that were “reshared” from Feed that used to be valued less because Instagram heard that people are more interested in seeing original Stories. But it saw a swell of reshared posts in big moments that people were expecting their Stories to reach more people than they did, so it relooked the value.
Another major consideration is misinformation. If you post something that third-party fact-checkers label as misinformation, Instagram doesn’t take it down, but a label is applied, and the Instagram algorithm shows the post lower in Feed and Stories. If you’ve posted misinformation multiple times, the Instagram algorithm may make all of your content harder to find.
Explore was designed to help you discover new things. The grid is made up of recommendations – photos and videos the Instagram algorithm finds for you, which is different from Feed and Stories, where most of what you see is from the accounts you follow.
To find photos and videos you might be interested in, Instagram looks at signals like what posts you’ve liked, saved, and commented on in the past. Once it’s found a group of photos and videos you might be interested in, it then orders them by how interested it thinks you are in each one. The most important signals the Instagram algorithm looks at, in order of importance, are:
- Information about the post, like how popular it seems to be. These are signals like how many and how quickly other people are liking, commenting, sharing, and saving a post. These signals matter much more in Explore than they do in Feed or Stories.
- Your history of interacting with the person who posted. It’s likely the poster is someone you’ve never heard of, but if you have interacted with them, that gives the Instagram algorithm a sense of how interested you might be in what they shared.
- Your activity – signals like what posts you’ve liked, saved or commented on and how you’ve interacted with posts in Explore in the past.
- Information about the person who posted, like how many times people have interacted with that person in the past few weeks.
Reels is designed to entertain you, and much like Explore, most of what you see is from accounts you don’t follow. Instagram goes through a similar process in ranking Reels as it does Explore.
With Reels, though, it’s specifically focused on what might entertain you. The most important predictions it makes are how likely you are to watch a reel all the way through, like it, and say it was entertaining or funny. The most important signals are:
Your activity – which reels you’ve liked, commented on and engaged with recently.
Your history of interacting with the person who posted
Information about the reel. These are signals about the content within the video like the audio track, video understanding based on pixels and whole frames, and popularity.
Information about the person who posted. Instagram’s algorithm considers their popularity to help find compelling content from a wide array of people and give everyone a chance to find their audience.
Contact Right Click Media today
So, while there is no single Instagram algorithm, there are a few tricks that can improve your post’s reach and engagement. Contact our team of social media experts and let us help build your Instagram presence and community.