Re: Advancing Distributed Moderation

Il 28/11/23 17:39, Evan Prodromou ha scritto:
> Email filtering has benefited greatly from relatively simple and 
> low-cost language processing methods such as naive Bayesian spam 
> filtering <https://en.wikipedia.org/wiki/Naive_Bayes_spam_filtering>. 
> These can balance a shared model (to allow collective protection) and 
> personal models (to customize for individual needs), with weighting on 
> each. [...]

I agree that's a sensible place where to look for inspiration. Email 
abuse gives us a pretty good idea of what's going to happen in the 
fediverse soon as it grows.

> I haven't seen a lot of precedent for asking spammers and harassers to 
> give consent to have their messages used for training public or private 
> filters, and I don't intend to ever do it for my email inbox or for my 
> social inbox.

This is a good point (this area of application of GDPR is wildly 
underexplored*) but there are some differences. For example, Mastodon 
will download a user's bio along with any message received, and the bio 
may contain all sorts of personal information. Nothing of the sort 
generally happens with email. It may take some vigilance for developers 
to keep the analogy valid (for example, dropping some of the received 
data before the filters and analyses are run).

Federico

(*) Whoever feels adventurous, try and send some GDPR art. 15 request to 
some giant provider like https://www.vadesecure.com/en/ ! Maybe we'll 
get some useful precedents in a couple years.
https://noyb.eu/en/exercise-your-rights

Received on Wednesday, 29 November 2023 09:40:54 UTC