Our profanity curation rule is based on a complex algorithm, which checks for phrases and words across different components of social posts like:
- Post's full text
- Author's username, ID, or screen name, according to the platform
- Author's full name
- Original tweet content in case of a ReTweet or a Tweet reply
Although our profanity filter checks for both compound phrases and single words, it does not search within words in particular (i.e., bass, grass).
Profanity rule by default is enabled in all the experiences. To check that out go to CURATE >> CURATION RULES
The current profanity detection supports the following languages:
If the language of the post is detected, the rule is applied for that specific language.
If the language of the post is not detected, it looks for a match across the different languages supported. If it finds a match the profanity rule is applied.