They are likely using those user ratings to build a model of what kind of comments bad users make.
Most of the bang for their buck was when they used a plain old sorting of those ratings. That already hid a lot of the sludge. The ML stuff is just a minor optimization compared to that.
Everything is just my opinion, of course, they're probably following a bunch of metrics I don't have access to and which could prove that the ML effort was worth it.
The comments got much better after Youtube added user ratings. Hardly "ML". I'm guessing they added ML later, but I haven't noticed any difference, to be honest...
And by "much better" I mean they went from amoeba level to early multi-cellular organism :)