Instagram Launches New Tools to Help Refine Content Recommendations
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. Read More...