Instagram Provides a New Overview of How its Algorithms Work

Looking to get a better understanding of the Instagram algorithm, and how it decides what content to show each individual user – and how you can use that to your own advantage?

You’re in luck – this week, as part of its Creator Week event, Instagram is providing some extra insight into its internal processes via series of explainers, with the first focused on the infamous feed algorithm, and how it actually dictates content reach in the app.

As explained by Instagram:

“We want to do a better job of explaining how Instagram works. There are a lot of misconceptions out there, and we recognize that we can do more to help people understand what we do. Today, we’re sharing the first in a series of posts that will shed more light on how Instagram’s technology works and how it impacts the experiences that people have across the app.”

The post covers a range of key elements that can help to facilitate more understanding, and improve your planning in the app. Here’s a look at the key points.

There’s not one, all-encompassing algorithm

Instagram first notes that its processes are not defined by a single algorithm, so the idea of ‘the algorithm’ as such is slightly flawed.

“Instagram doesn’t have one algorithm that oversees what people do and don’t see on the app. We use a variety of algorithms, classifiers, and processes, each with its own purpose. We want to make the most of your time, and we believe that using technology to personalize your experience is the best way to do that.”

Instagram explains that, like Facebook, it implemented an algorithm because the flow of content became too much for each user to navigate.

“By 2016, people were missing 70% of all their posts in Feed, including almost half of posts from their close connections. So we developed and introduced a Feed that ranked posts based on what you care about most.”

Which is why the focus of its feed and Stories algorithms is generally on friends, while Explore and Reels look to uncover more relevant topics based on trends, interests, etc.

Key signals

Instagram says that its algorithms all use key signals, with those signals varying dependent on each element.

Instagram notes that there are “thousands” of signals that its systems can draw from, but for the most part, the main indicators across Feed and Stories, in order of importance, are:

  • Information about the post – These are signals both about how popular a post is – think how many people have liked it – 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 for 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.

  • Your activity This helps us 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 us a sense of how interested you are generally in seeing posts from a particular person. An example is whether or not you comment on each other’s posts.

These are the general algorithm identifiers, similar to Facebook’s News Feed, with the key elements being what types of posts you engage with and your relationship to the creator of each.

If you engage with video more often, you’ll see more video, if the post is getting a lot of engagement, you’re more likely to see it, if you tap Like on a certain post, that’s a strong indicator of interest, etc.

Worth noting here that these elements apply to both the main feed and your Stories, so if you’re looking to maximize reach in these surfaces, these are the key elements that you need to focus on.

Furthering this, Instagram also notes that the feed ranking will also be based on each users’ engagement history:

“In Feed, the five interactions we look at most closely 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 an action, and the more heavily we weigh that action, the higher up you’ll see the post.”

Again, it comes down to incentivizing action – how can you maximize the appeal of your content to prompt these types of responses? That will help ensure more of your posts get priority for each user.

Ranking Explore

Inatsgram’s discovery tab is a little different, with the Explore algorithm focused on showing you other content that you may like, based on who you follow and your engagement history.

“To find photos and videos you might be interested in, we look at signals like what posts you’ve liked, saved, and commented on in the past. Let’s say you’ve recently liked a number of photos from San Francisco’s dumpling chef Cathay Bi. 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 Dragon Beaux. In that case, the next time you open Explore, we might show you a photo or video from Dragon Beaux. 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.”

So the idea here is that the algorithm will look to showcase content to related groups of people based on clusters – if you’re regularly engaging with a profile that shares fishing content, then it’s likely that other people who engage with the same are also looking at other fishing accounts, which you may also be interested in.

This is where hashtags can help improve discovery, by getting your account in front of people searching for certain topics. If they then engage with your posts, that increases your chances of being shown to their connections, and so on.

Like Feed and Stories, Instagram ranks the Explore listing based on how likely each user is to engage with each post.

Once we’ve found a group of photos and videos you might be interested in, we then order them by how interested we think you are in each one, much like how we rank Feed and Stories. The best way to guess how interested you are in something is to predict how likely you are to do something with the post. The most important actions we predict in Explore include likes, saves, and shares.”

Saves have become a more important consideration more recently, with some noting that Saves have more weight in algorithm distribution, which may or may not be correct. But certainly, it’s an element that Instagram is now specifically noting, so it is worth considering how you can incentivize saves of your posts, as this can play a part in improving Explore exposure.

It’s worth also noting too, that while the Explore feed is also ranked based on personal engagement elements (the types of post a user has engaged with, relationship with account, etc.), how popular a post is, based on broader engagement signals, is a much bigger consideration in Explore, and will see content get more exposure in the Explore feed.

Ranking Reels

Instagram’s latest algorithm-defined element is its TikTok like Reels, for which it says the algorithm is “specifically focused on what might entertain you.”

We survey people and ask whether they find a particular reel entertaining or funny, and learn from the feedback to get better at working out what will entertain people, with an eye towards smaller creators. The most important predictions we make are how likely you are to watch a reel all the way through, like it, say it was entertaining or funny, and go to the audio page (a proxy for whether or not you might be inspired to make your own reel.)”

TikTok has almost perfected the most engaging version of the short video algorithm, with its system taking in the exact right signals to show you a constant stream of content that you can’t help but keep scrolling through, based on trends, creators, the content of each clip, etc.

Instagram is now working to catch up, and anecdotally, it is improving, with its Reels display hooking into similar elements to make it a more sticky, engaging proposition for users who tap into the Reels feed.

For Reels, Instagram says that these are the four key elements of focus in its algorithm:

  • Your activity We look at things like which reels you’ve liked, commented on, and engaged with recently. These signals help us to understand what content might be relevant to you.

  • Your history of interacting with the person who posted Like in Explore, it’s likely the video was made by someone you’ve never heard of, but if you have interacted with them that gives us a sense of how interested you might be in what they shared.

  • Information about the reel These are signals about the content within the video such as the audio track, video understanding based on pixels and whole frames, as well as popularity.

  • Information about the person who posted We consider popularity to help find compelling content from a wide array of people and give everyone a chance to find their audience.

So content and creator popularity, overall, is a bigger factor for Reels, while it’s also worth noting that Instagram will restrict the reach of Reels that include a TikTok watermark or similar, which it says is designed to improve the user experience (i.e. people criticized Reels as simply being a re-hashed feed of TikTok clips, so it now looks to stop such re-sharing).

These are some helpful pointers as to how Instagram’s various algorithms work, and how it looks to showcase certain content to users – and what each creator should be focused on to improve their reach. Essentially, it comes down to audience understanding – doubling down on what works, and dropping what people don’t respond to – in order to maximize these key elements, and boost engagement, first with your followers, then subsequently with wider audiences.

Some important notes to factor into your IG planning. You can read Instagram’s full algorithm explainer, which also includes notes on Shadowbanning, here.

Source: www.socialmediatoday.com, originally published on 2021-06-08 15:32:29