Docs / Moderation / Text Moderation / Text Moderation categories

Text Moderation categories

Here is the list of public text analysis and text moderation models that you can use.

Models for Image and Video Recognition are available here.

Text classification

Detect messages containing sexual content, hate, violence, insults or toxic content

Advanced rules and pattern-matching to detect unwanted content

Detect hate, toxic, obscene or sexual language

Detect personally identifiable information (PII): email addresses, phone numbers and more

Determine if a domain name or link is unsafe, or unwanted

Automatically detect the language of a given text or user message

Prevent users from choosing misleading usernames

Create custom allow or disallow lists for custom needs

Detects names, slogans and expressions related to extremist ideologies

Detects names and words related to recreational drugs

Detects weapon-related names and terms

Detects words and expressions related to medical drugs