Meta

Meta
Policies
Community StandardsMeta Advertising StandardsOther policiesHow Meta improvesAge-Appropriate Content

Features
Our approach to dangerous organizations and individualsOur approach to the opioid epidemicOur approach to electionsOur approach to misinformationOur approach to newsworthy contentOur approach to Facebook Feed rankingOur approach to explaining rankingAccessibility at Meta

Research tools
Content Library and Content Library APIAd Library ToolsOther research tools and data catalogue

Enforcement
Detecting violationsTaking action

Governance
Governance innovationOversight Board overviewHow to appeal to the Oversight BoardOversight Board casesOversight Board recommendationsCreating the Oversight BoardOversight Board: Further asked questionsMeta’s Bi-Annual Updates on the Oversight BoardTracking the Oversight Board's Impact

Security
Threat disruptionsSecurity threatsThreat reporting

Reports
Community Standards Enforcement ReportIntellectual PropertyGovernment Requests for User DataContent Restrictions Based on Local LawInternet DisruptionsWidely Viewed Content ReportRegulatory and Other Transparency Reports

Policies
Community Standards
Meta Advertising Standards
Other policies
How Meta improves
Age-Appropriate Content
Features
Our approach to dangerous organizations and individuals
Our approach to the opioid epidemic
Our approach to elections
Our approach to misinformation
Our approach to newsworthy content
Our approach to Facebook Feed ranking
Our approach to explaining ranking
Accessibility at Meta
Research tools
Content Library and Content Library API
Ad Library Tools
Other research tools and data catalogue
Enforcement
Detecting violations
Taking action
Governance
Governance innovation
Oversight Board overview
How to appeal to the Oversight Board
Oversight Board cases
Oversight Board recommendations
Creating the Oversight Board
Oversight Board: Further asked questions
Meta’s Bi-Annual Updates on the Oversight Board
Tracking the Oversight Board's Impact
Security
Threat disruptions
Security threats
Threat reporting
Reports
Community Standards Enforcement Report
Intellectual Property
Government Requests for User Data
Content Restrictions Based on Local Law
Internet Disruptions
Widely Viewed Content Report
Regulatory and Other Transparency Reports
Policies
Community Standards
Meta Advertising Standards
Other policies
How Meta improves
Age-Appropriate Content
Features
Our approach to dangerous organizations and individuals
Our approach to the opioid epidemic
Our approach to elections
Our approach to misinformation
Our approach to newsworthy content
Our approach to Facebook Feed ranking
Our approach to explaining ranking
Accessibility at Meta
Research tools
Content Library and Content Library API
Ad Library Tools
Other research tools and data catalogue
Security
Threat disruptions
Security threats
Threat reporting
Reports
Community Standards Enforcement Report
Intellectual Property
Government Requests for User Data
Content Restrictions Based on Local Law
Internet Disruptions
Widely Viewed Content Report
Regulatory and Other Transparency Reports
Enforcement
Detecting violations
Taking action
Governance
Governance innovation
Oversight Board overview
How to appeal to the Oversight Board
Oversight Board cases
Oversight Board recommendations
Creating the Oversight Board
Oversight Board: Further asked questions
Meta’s Bi-Annual Updates on the Oversight Board
Tracking the Oversight Board's Impact
Policies
Community Standards
Meta Advertising Standards
Other policies
How Meta improves
Age-Appropriate Content
Features
Our approach to dangerous organizations and individuals
Our approach to the opioid epidemic
Our approach to elections
Our approach to misinformation
Our approach to newsworthy content
Our approach to Facebook Feed ranking
Our approach to explaining ranking
Accessibility at Meta
Research tools
Content Library and Content Library API
Ad Library Tools
Other research tools and data catalogue
Enforcement
Detecting violations
Taking action
Governance
Governance innovation
Oversight Board overview
How to appeal to the Oversight Board
Oversight Board cases
Oversight Board recommendations
Creating the Oversight Board
Oversight Board: Further asked questions
Meta’s Bi-Annual Updates on the Oversight Board
Tracking the Oversight Board's Impact
Security
Threat disruptions
Security threats
Threat reporting
Reports
Community Standards Enforcement Report
Intellectual Property
Government Requests for User Data
Content Restrictions Based on Local Law
Internet Disruptions
Widely Viewed Content Report
Regulatory and Other Transparency Reports
English (US)
Privacy PolicyTerms of ServiceCookies
Home
Features
Explaining Ranking
Instagram Comments

Instagram Comments AI system

UPDATED MAR 7, 2025
The content you see on your Instagram Comments is selected, ranked and delivered to you by an artificial intelligence (AI) system. Within one AI system, multiple machine learning models work together to deliver your experience. These models and their input signals are dynamic and they change frequently as the system learns and improves over time.

Overview of Instagram Comments

When you view and interact with Instagram, one of the underlying AI systems delivers comments on posts in an order of relevance to you.
How Instagram Comments works
The AI system behind Instagram Comments automatically determines which comments on posts you'll see first by predicting what you’re most likely to be interested in. These predictions are based on a variety of factors, including the general relevance and popularity of the comments, as well as your recent activities on Instagram. Here’s how it works:
  1. Display most important comments first
    The system shows comments that may be most relevant to you at the top of each comment thread. These might include your own comments, your friends’ comments or pinned comments.
  2. Score and order comments
    Next, the system calculates a score for other comments on a post based on multiple input signals, including the relevance of the comment to the post and how popular the comment is among all viewers. Comments are then ordered by their scores.
  3. Apply filters
    Finally, the system applies filters to remove any comments that may go against our Community Guidelines.
How to customize what you see
Your experience on Instagram Comments is personalized based on your activity, and you have options to control or customize what you see. Below, we describe how to do this with different in-product features. Options shown here may not be available to everyone.
See newest comments first
To view comments in reverse chronological order, tap "Most recent" in the drop-down menu for the comments section.
See comments from Meta Verified users first
To view all comments from Meta Verified users first before other comments, tap “Meta Verified" in the drop-down menu for the comments section.
See only comments from subscribers (for Creators)
To filter out comments and only see those from your subscribers, tap “Subscribers only” in the drop-down menu for the comments section.
How the AI delivers content to you
We want you to see content you enjoy and find interesting. To achieve this, the AI system has models that help it make predictions about content you'll find most relevant and valuable. These prediction models use underlying input signals to help select content you're most likely to engage with.
Below are some of the significant predictions–and input signals that inform them–that we use in this AI system.
How likely you are to report a comment you think goes against our Community Guidelines. Comments less likely to be reported are ranked higher
Signals influencing this prediction include:
  • If you have unfollowed the comment author in the past
  • How frequently users have taken action to report comments on the post
  • How many times you have previously reported comments
  • How long ago the comment was posted
  • viewer is author or not
How likely you are to reply to delete a reply on your own post
Signals influencing this prediction include:
  • number of comments deleted
  • what surface the comment is on (Feed, Reels etc)
  • How frequently the user deletes the comment
  • word count of the comments deleted
  • viewer is author or not
How likely you are to reply to the comment or any of its replies
Signals influencing this prediction include:
  • What surface the comment you are viewing is on (Feed, Explore, Reels, etc.)
  • If you are the post author or not
  • How many likes the comment has
  • How frequently you comment on posts and reply to comments on posts
  • How many comments you have made on posts created by this author
How likely you are to scroll past the comment without reading it or any of its replies
Signals influencing this prediction include:
  • How many likes the post has
  • How many likes and replies the comment has
  • What surface the comment you are viewing is on (Feed, Explore, Reels, etc.)
  • How much time you usually spend on a comment surface
  • How many comments you have interacted with in the past
Whether or not you will click to like a comment or any of its replies
Signals influencing this prediction include:
  • How often you like comments
  • viewer is author or not
  • The word counts for comments that you have liked
  • How many comments and posts you have liked in the past
  • How many likes the comment has
Meta
Transparency Center
Policies
Enforcement
Security
Features
Governance
Research tools
Reports
English (US)