📖 Content moderation glossary
What is a false positive in moderation?
In short
In moderation, a false positive is legitimate content that is wrongly identified as breaking the rules and therefore hidden, removed or flagged when it should have stayed visible.
False positives are the visible side of over-moderation. A reader who sees their reasonable comment disappear feels censored, and may say so loudly elsewhere. For a news publisher or a public body, removing legitimate criticism is a reputational risk in itself.
Example: a keyword filter blocks the comment 'the Scunthorpe match was great' because the town's name contains a banned string. Another classic: a comment quoting an insult in order to condemn it is removed as if it were the insult itself.
Lowering false positives means using models that read context, setting thresholds carefully, sending doubtful cases to people and letting users contest decisions. OpenModeration keeps criticism visible, hides automatically only clear violations, and records a written reason for every decision so errors can be spotted and corrected.