Setting up spam detection in your community

[NateDhaliwal]

@Saif

Could you explain this further with an example?

Sure. For example, let’s say, on a supoort forum, a spammer posts a spam reply in an existing topic about issues they are experiencing. The OP and people answering are not the same user as the spammer. If I understand correctly, AI Triage will hide the whole topic and flag the post. Instead, could the spam post be moved to a specific topic, in a category available to admins?

I was wondering this as I read this post.

@Saif

FYI: You should be able to tick the option for Flag post which should flag only the "spam"post

Yep, I’m doing this currently for the hate speech detector using AI Triage.

@Saif

@sam

Differences from AI triage

See the differences outlined below

While spam detection is designed specifically for identifying spam, AI triage supports broader post management tasks.

Feature	AI Spam Detection	AI Triage
Complexity	Streamlined, opinionated setup	Highly customizable and flexible
Primary use case	Detecting spam with minimal overhead	Advanced workflows for categorization, tagging, replies, spam detection, nsfw detection
Actions	Flags spam, silences users	Tags, categorizes, hides posts, adds replies, flags posts, silences users
Recommendation	Use instead of Akismet	Use for rich highly customizable workflows

For more details, see Discourse AI - AI triage.

Lol, how could I miss that …