/
Navigation
Chronicles
Browse all articles
Explore
Semantic exploration
Research
Entity momentum
Nexus
Correlations & relationships
Story Arc
Topic evolution
Drift Map
Semantic trajectory animation
Posts
Analysis & commentary
Pulse API
Tech news intelligence API
Browse
Entities
Companies, people, products, technologies
Domains
Browse by publication source
Handles
Browse by social media handle
Detection
Concept Search
Semantic similarity search
High Impact Stories
Top coverage by position
Sentiment Analysis
Positive/negative coverage
Anomaly Detection
Unusual coverage patterns
Analysis
Rivalry Report
Compare two entities head-to-head
Semantic Pivots
Narrative discontinuities
Crisis Response
Event recovery patterns
Connected
Search: /
Command: ⌘K
Embeddings: large
TEXXR

Chronicles

The story behind the story

days · browse · Enter similar · o open

Instagram details how the app ranks Feed content, Stories, Reels, and more, and tests more user controls, including an Interested button for recommended posts

Aisha Malik / TechCrunch :

TechCrunch Aisha Malik

Context & Ripple Effects

Instagram had already publicly explained ranking across its core surfaces in an earlier ranking-system explainer, while recommendations had expanded beyond posts from accounts a user follows through Recommended For You. This update extends that transparency-and-feedback approach across Feed, Stories, and Reels.

The controls matter because recommendation quality depends not only on inferred behavior but also on explicit signals. Instagram’s later topic-level algorithm customization shows how this kind of feedback can evolve into a more visible user-facing layer.

First-order effects

  • Users in the test can explicitly mark recommended posts as interesting, giving Instagram a new direct relevance signal alongside behavioral signals.
  • Creators and publishers gain clearer guidance on the ranking factors Instagram says it uses across Feed, Stories, and Reels, although the reported control is still a test rather than a platform-wide change.

Second-order effects

  • A stronger explicit-feedback loop can change which recommended posts receive distribution, pushing creators to optimize for sustained user interest rather than only passive engagement.
  • Other recommendation-driven products face greater pressure to explain ranking inputs and offer meaningful preference controls, not merely opaque personalization.

Third-order effects

  • If such controls broaden, social recommendation may shift from platforms inferring preferences in the background toward a hybrid model in which users actively steer their feeds.
  • That shift can make recommendation systems more accountable to users, while also making the design of feedback controls a central competitive and trust issue.

The trend: Instagram is part of a broader move to make algorithmic recommendation systems more legible and more directly steerable by users.

Discussion

  • @taylorannabell Taylor Annabell on x
    👀 “While we've heard some people believe you need to pay for ads to achieve better reach, we don't suppress content to encourage people to buy ads. It's a better business to make Instagram more engaging overall by growing reach for those who create the most engaging content...” h…
  • @mosseri Adam Mosseri on x
    How the “Algorithm” Works 📝 - “The Algorithm” (or actually algorithms) - Ranking Stories - Ranking Feed - Ranking Reels - Ranking Explore - “Shadowbanning” - How to Grow Your Audience More details here: https://about.instagram.com/ ... [video]
  • @kei_maye Kei Maye on x
    Nah I'm sorry - the part about them “not suppressing reach in order to get people to pay for ads” I'm not buying it. Any time I use promotional language, my posts get BURIED. Everytime I write £ or mention anything sales related - the same thing happens every time. https://twitte…
  • @zamaan_qureshi Zamaan Qureshi on x
    Cool, except Mosseri left out that the majority of Facebook's data collection happens when people aren't knowingly interacting with Facebook's products (UK Competition and Markets Authority report). Think about all that third-party data. Of course, he's not gonna mention it. http…
  • @christinasbg Christina Jovanna Olivarez on x
    Engagement is IMPORTANT ✅ Being descriptive with your captions and post is IMPORTANT ✅ https://twitter.com/...
  • @hagazo @hagazo on x
    @mosseri Im about to watch the video but before i must leave here my discontent on how IG is nowadays Infinite timeline, lots of stuff being shown to me that i don't want to see, nor follow, nor care. Lots of same “viral videos” appearing all the time, taking the spot of content …
  • @titterdaily @titterdaily on x
    @mosseri Why don't y'all open source your algorithm so we can get more transparency on what y'all shadowban?