Auto-moderation of user-generated content

Booklet has protections to make sure that objectionable content doesn’t show up in your forum and newsletter. Booklet screens all Posts, Replies, and Member Profiles with OpenAI’s Moderation API. By default, it hides any content flagged by OpenAI Moderation for you to review. You can also optionally deactivate accounts that post disallowed content.

Admins can manage moderation settings (including disabling them) under “Settings -> Moderation”.

How it works

Booklet uses OpenAI’s Moderation API to analyze user-generate contents.

It automatically reviews each:

  • Post
  • Reply
  • Member profile

If OpenAI API flags content as objectionable, then that content is hidden for review. All admins of the community will receive an email whenever content is hidden for review.

Admins can then unhide or delete content.

Hidden content is still visible to the user that posted it. But, it is not visible to other members until it is reviewed, and it will not be included in the newsletter.

Content from Admins is not moderated.

Optionally, you can choose to auto-deactivate accounts that post objectionable content. This means that the user will no longer be able to sign in, post, reply, or receive updates.

If you allow open signups, we recommend keeping enabling all moderation settings to keep your community safe.