I highly doubt it.
I’m pretty sure typical harassment comes in the form of many similar messages by many different users joining a bandwagon. Moderation wouldn’t really be fast enough to stop that; indeed, Twitter’s current moderation scheme isn’t fast enough to stop it. But the current scheme is capable of penalizing people after the fact, particularly the organizer(s) of the bandwagon, and that creates some level of deterrence. An opt-out moderation scheme would be less effective as a deterrent, since the type of political influencers that tend to be involved in these things could likely easily convince their followers to opt out.
That may be a cost worth paying for the sake of free speech. But don’t expect it to make the anti-harassment side happy.
That said, it’s not like that side can only tolerate (what this post terms as) censorship. On the contrary, they seem to like Mastodon and its federated model. I do suspect that approach would not work as well at higher scale - not in a technical sense, but in terms of the ability to set and enforce norms across servers. But that’s total speculation, and I haven’t even used Mastodon myself…
Social media keep using this excuse for not trying. We can moderate spam in emails with a simple naive bayes classifier, why don't we just do that with comments? It could easily classify comments that are part of a bandwagon and flag them automaticly hiding them or for human review.
We are able to moderate email but the concepts we use to do so are never applied to comments, I don't know why, this seems like a solved problem.
In SMTP servers I've managed for clients we typically block anywhere from 80 to 99.999% (yes 10000 blocked to one success) messages. I'd call that MegaModeration if there was such a term.
And if you think email spam is solved then I don't believe you read HN often as there is a common complaint of "Gmail is blocking anything I send, I'm a low volume non-commercial sender"
In addition email filtering is extremely slow to react to new methods, generally taking hours depending on the reporting system.
Lastly, you've not thought about the problem much. How are you going to rapidly detect the difference between a fun meme that spreads virally versus an attack against an individual. Far more often you're going to be blocking something that's not a bad thing.
I get that no machine learning is 100% perfect which is why it should be used as an indicator rather than the deciding factor.
I have had issues with gmail blocking emails but as you point out it was always because of ip reputation not over zealous Naive Bayes.
[1] https://demos.co.uk/press-release/staggering-scale-of-social...