Moderation

Moderation rules

Configure filters for spam, profanity, negativity, links, contact details, keywords, images, and high-intent comments.

Rule types

  • AI profanity and negativity filters catch abusive or brand-damaging comments.
  • URL, email, and phone filters hide contact-bait and phishing attempts.
  • Keyword rules hide banned phrases, spam patterns, or campaign-specific problems.
  • Image, emoji, and mention filters reduce low-quality comment patterns.
  • Needs-reply labels surface questions, complaints, and buyer intent for human review.

Recommended first setup

Start with hide actions for spam, links, profanity, and obvious abuse. Use labels for comments that need judgment. Reserve delete actions for clear violations where you do not need a reversible action.

Testing rules

Review matched comments during the first few days of a campaign. Tighten keyword rules only after you see false positives, and add allowlist terms for product names or phrases that should remain visible.

Ready to put the docs to work?

Request controlled access when you are ready to evaluate CommentProtect with your Meta workflow.