Instagram Expands Feed Personalization to Topics

Instagram just made it a whole lot easier to control what you see in your main feed. The app expanded its algorithm personalization feature to its central feed so users can choose exactly what topics they want to see more and less of in their recommendations.

According to Instagram chief Adam Mosseri, the change is meant to give users more "agency" over their experience in the app. "I believe it's in our best interest as a business to empower people to shape Instagram into something that works for them, and that people should be able to have a meaningful amount of agency over the products they spend so much time in," he wrote in a lengthy post on Threads.

But that "agency" apparently doesn't apply to people who want to see more posts from accounts they actually follow. The feature only works with interest-based topics, like "rescue dogs" or "parenting humor." When I tried asking for "posts from people I follow" it returned an error message that said "no results found."

The issue is a sore spot for many creators and businesses on the platform. Mosseri is regularly questioned about why creators' posts don't consistently reach all, or even most, of their followers. In his post about the new algorithm controls, he acknowledges some of that frustration. "Who you follow used to be a meaningful tool people had for shaping their own experience, and as recommendations took over the main feed that tool quietly stopped working," he writes. "Leaning into content from accounts you do not follow became an inevitability as the industry accepted that personal moments were moving to stories and DMs for good. A feed where one in fifty friends posts a polished moment isn't interesting, and algorithmic recommendations filled that gap."

But while it doesn't sound like Instagram plans to scale back recommendations overall — the app does offer a dedicated "following" feed — the company is looking at ways to take more of users' preferences into account. Mosseri says Instagram's new personalization features are possible thanks to large language models, which have helped demystify previously inscrutable algorithms. Eventually, these same tools could enable an even deeper level of personalization or a completely "bespoke" version of the app. For now, he says, the company is "actively working on supporting requests for people, different moods or vibes, content types, and more."