Text Moderation categories
Here is the list of public text analysis and text moderation models that you can use.
Text classification
Rule-based moderation
Rule-based Moderation
Advanced rules and pattern-matching to detect unwanted content
Profanity Detection
Detect hate, toxic, obscene or sexual language
Personal Information
Detect personally identifiable information (PII): email addresses, phone numbers and more
URL and Link Moderation
Determine if a domain name or link is unsafe, or unwanted
Language Detection
Automatically detect the language of a given text or user message
Misleading Usernames
Prevent users from choosing misleading usernames
Custom (dis)allow lists
Create custom allow or disallow lists for custom needs
Extremism detection
Detects names, slogans and expressions related to extremist ideologies
Drug detection
Detects names and words related to recreational drugs
Weapon detection
Detects weapon-related names and terms
Medical drug detection
Detects words and expressions related to medical drugs