I just shipped a transformer-based SocialNLP toolkit for @farcaster.  This library can possibly help construct new ML-based feed algorithms based on text classification instead of relying on manual curation, recasts/reactions, and chronological ordering.

Check it out:

A sufficiently decentralized social network. farcaster.xyz

I just shipped a transformer-based SocialNLP toolkit for @farcaster.  This library can possibly help construct new ML-based feed algorithms based on text classification instead of relying on manual curation, recasts/reactions, and chronological ordering.

Check it out:
https://github.com/michaelhly/FarGlot

We can also use this tool kit to train our own classifier models for reputation ranking, spam detection, and auto-moderation.

Here is an example:

@launch FarGlot: A Transformer-based SocialNLP toolkit for @farcaster

We can also use this tool kit to train our own classifier models for reputation ranking, spam detection, and auto-moderation.

Here is an example:
https://github.com/michaelhly/FarGlot/blob/master/examples/text_classification.py

@operator & /operator | building future.news | BCI, bioinformatics, search, chaos, decentralized AI

- we'll first have to come up with heuristics on what classifies spam (i.e. create a test set based on what users report)
- and then train a model to minimize loss
- the nature of spam can change, and we'll have to re-tune

in short — it depends on how good we're at classifying ("labeling") spam

Nice. Do you suspect that there's a big difference between the text of a spam cast and a legitimate one?