blakejakopovic/nostr-spam-detection

An experiment in building a machine learning model to label Nostr spam content for filtering and relay rejection.

29
/ 100
Experimental

This project helps Nostr relay operators or developers filter out unwanted content. It takes raw Nostr event content and determines if it's spam or legitimate, outputting a clear label and a spam score. This allows you to automatically reject or flag undesirable messages on your relay.

No commits in the last 6 months.

Use this if you are a Nostr relay operator looking to automatically identify and filter spam events before they hit your users.

Not ideal if you need to detect spam in languages other than Asian languages (for spam) or English (for non-spam), or if your definition of spam differs significantly from recent Nostr spam trends.

Nostr relay-management content-moderation spam-filtering decentralized-social-media
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

24

Forks

2

Language

Jupyter Notebook

License

MIT

Last pushed

Feb 25, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/blakejakopovic/nostr-spam-detection"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.