The secret sauce of TikTok’s massive success is its highly attuned algorithm, which learns, literally within minutes, what you want to see more of, what you don’t like, and then translates that into an increasingly addictive stream of short video clips in the app.

Instagram knows this, which is why it’s now leaning into more AI-fueled recommendations, which it says have increased engagement significantly since being integrated into user feeds.

But that’s clearly not enough, because today, Instagram has announced some new features designed to help users provide more direct input into what they’re shown in the app, in order to further align their IG feed to their preferences.

First off, as you can see in the first image above, Instagram says that it’s testing the ability to mark multiple posts in Explore as ‘Not Interested’, in order to streamline your algorithmic training process.

“We’ll immediately hide those posts and refrain from showing you similar content in the future.”

That could help you get rid of a heap of junk at once, which should, theoretically, show Instagram that you’re really not interested in whatever topics you choose to highlight.

Which should work – but then again, I still get a lot of random or tangentially related recommendations in Explore, which keep coming up, even as I specifically tell IG that I’m not interested.

Maybe, then, sending the app bulk responses will better underline this.

As displayed in the second image, Instagram will also soon begin testing the capacity for users to tell Instagram that they don’t want to see suggested posts with certain words, phrases or emojis in the caption or included tags.

“Whether you’re seeing something that’s not relevant, or have moved on from something you used to like, you can use this feature to stop seeing content that’s not interesting to you.”

In combination, the new self-reporting features should better enable users to make Instagram more relevant to them, while also helping Instagram’s engineers to get a better understanding of which related recommendations work, and which are annoying people, in order to refine their automated content highlights in-stream.

Though it’s not on the same level as TikTok, in that users will have to manually provide that feedback, while TikTok’s AI system seems much better at determining variable elements in posts, and responding to direct user activity.

The fact of the matter is that, no matter what manual tools IG provides on this front, many users simply won’t use them – but again, maybe by incorporating the knowledge that people do provide, that will help to better inform its automated recommendations for everyone either way.

In addition to these new options, Instagram has also provided a basic overview of its current recommendation system – which, as noted, utilizes machine learning, based on your past actions in the app, to find more things that you may be interested in.

As explained by Instagram:

“One of the ways we personalize your feed is by predicting how likely you are to do something with a post you see. 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 in your feed.”

On this front, Instagram says that there are five specific interaction metrics that it uses to guide its recommendation system:

• Dwell time on posts
• The likelihood of a user commenting on a post
• The likelihood of a user liking a post
• The likelihood of a user re-sharing a post
• The likelihood of a user tapping though to the creators’ profile

In the recent past, it has seemed like re-shares have been given more priority, which would align with Instagram’s broader mission to help amplify creators in the app.

Instagram doesn’t specify that any one of these elements is weighted more heavily than the other, but if you’re looking to optimize your IG posting process, these are the key interactions that the platform’s algorithm focuses on in determining what to show each user more of.

How do you use that as a social media marketer? Posting content that’s visually appealing will help to improve dwell time (easier said than done, I know), while prompting comments, maybe by posting community questions could be another way to boost engagement.

(It’s also worth noting that ‘saves’, which had been highlighted as a key metric of focus by some social media marketing commentators, are not specifically mentioned in this new overview.)

In combination, the new tools and insights provide some more guidance on Instagram’s recommendation tools and process, which can help you better understand how the platform is looking to highlight certain posts, in alignment with user preferences.

Over time, these new manual feedback elements will help to refine its algorithmic systems – though whether they can get close to TikTok on this front remains to be seen.