This help doc will walk you through custom profanity and language moderation options available. Steps below outline the ability to do this at both the account and the project level.
Please note: This feature is only available on certain subscription levels. Please reach out to your account manager to discuss an upgrade if needed.
Navigate to your Account Dashboard and select Account Settings. Select the Auto Moderation tab at the top of the page.
Navigate to the Project Dashboard and Select Auto Moderation.
Match List: A response will be moderated (hidden from the public) if it contains an expression present in the Match List.
To add words or expressions - type them into the box and click the + button to the right.
Exception List: A match will be checked against this list, and if the match contains an exception then the response will not be moderated. This can be used to stop auto-moderating responses containing the “exception” text.
Expressions are NOT case sensitive.
The plural of a word in this list will automatically be detected.
REGEXPS can be used
Most profanity will automatically be detected when the Global