[Backend] ML-assisted content moderation queue

[Penielka]

Overview

Scale content moderation with ML pre-screening: submissions are scored for policy violations, high-risk items go to a human queue, and moderator decisions feed back to improve the model.

Acceptance Criteria

• ML pre-screening scores submissions for policy risk
• High-risk items routed to a human review queue
• Moderator decisions recorded and fed back for retraining
• Moderation actions (approve/reject/flag) enforced downstream
• Appeal flow for rejected content

Files to Modify

• backend/src/services/moderation/ — scoring and queue
• backend/src/workers/moderationJob.ts — async scoring
• frontend/src/app/admin/content/moderation/ — review UI
• backend/src/routes/moderation.ts — endpoints

Priority: Medium

[iyanumajekodunmi756]

I would love to work on this issue

[grantfox-oss]

🦊 GrantFox — @iyanumajekodunmi756 has been assigned to this issue as part of the Third Campaign campaign!

Next steps:

1. Open a Pull Request referencing this issue (e.g., Closes #402)
2. Your PR will be reviewed by the AetherEdu maintainers

Good luck! Track your progress on GrantFox.

[grantfox-oss]

🎉 This issue has been marked as completed on GrantFox as part of the Third Campaign campaign!

@iyanumajekodunmi756's PR #449 was approved and merged by @Penielka.

🏆 @iyanumajekodunmi756: You earned 40 FoxPoints for this contribution! Your current tier: Builder (1,940 total points). Track your full progress on GrantFox.

👏 Great work, @iyanumajekodunmi756! Keep contributing to AetherEdu.