AI Moderation Settings

Overview

TNL’s AI Moderation system automatically reviews Community content to detect and filter harmful or inappropriate material before it becomes visible.

You can configure:

Post moderation
Comment moderation
Sensitivity thresholds
Custom blacklists
Username restrictions

Access AI Moderation

Go to Community Menu
Select AI Moderation

Enable AI Content Moderation

Toggle on:

Moderate Posts
Moderate Comments

When enabled, AI reviews content before it is published.

Moderation Categories

You can configure sensitivity thresholds for different content categories.

Lower thresholds = stricter moderation.

Categories include:

Hate speech
Sexual content
Sexual content involving minors
Harassment
Violence
Self-harm
Illicit activity (e.g., advice on illegal acts)
Threatening content
Weapon references

Each category has:

Review Threshold
Auto-Block Threshold

How Content Scoring Works

AI assigns a content score:

0–30% → Automatically Approved
30–60% → Flagged for Manual Review
Above 60% → Automatically Blocked

Flagged or blocked content appears in the Review Tab for each group.

Content Lists (Custom Blacklists)

To manage custom filtering:

Go to Community Menu
Select Content Lists

Blacklisted Words

Add words that should never appear in posts.

Words are checked in addition to AI moderation.
You can manage global swear word lists by language.
Add company-specific overrides to allow or block specific words.

Blacklisted Usernames

You can block specific username patterns.

Prevents certain words or formats from being used during registration.

Best Practices

Enable both post and comment moderation.
Use stricter thresholds for sensitive brands.
Regularly review flagged content.
Add brand-specific blacklisted words.
Set appropriate report thresholds in Community Settings.
Combine AI moderation with manual approval if needed.

AI Moderation helps maintain a safe, positive, and brand-aligned Community environment.