📖 Content moderation glossary
What is a false negative in moderation?
In short
In moderation, a false negative is content that breaks the rules but is not detected, so it stays visible when it should have been hidden or removed.
False negatives are the misses of a moderation system: the insult written with numbers instead of letters, the scam link hidden behind a URL shortener, the harassment that only makes sense if you know the previous ten comments.
Example: under a brand's giveaway post, a fake account copying the brand's name replies to every participant with 'you won, claim your prize here'. If moderation misses it, customers may hand over their bank details to a fraudster.
There is always a trade-off between false negatives and false positives: a stricter threshold catches more abuse but removes more legitimate content. The right balance depends on the audience and the risk, which is why moderation rules should be set per client and per use case, as OpenModeration does.