Text Moderation Principles

Introduction

Sightengine's Text Moderation API is useful to moderate any type of text contents: comments, messages, chats, posts and even usernames.

The categories of content that are detected are:

• Profanity: insults, discriminatory content, sexual content or other inappropriate words and phrases. More on Profanity moderation
• Personal Details: typically email addresses, phone numbers, IPs, US social security numbers etc. that qualify as personally identifiable information and should be hidden. More on PII detection.
• Links: URLs to external websites and pages. We can also help you flag domains and pages known to host unsafe or unwanted content. More on URL moderation
• Misleading usernames: usernames that intend to mislead other users or cause errors. More on Misleading username moderation
• Custom disallow list: specific words that you need to catch. Could be words specific to your community, could be a list of competitor names, etc. More on custom disallow lists

You can also implement a custom whitelist to force our API to disregard any words or content you feel shouldn't be flagged.