Twitter's big QA problem after harassment is people who tweet well about X (and worth following for X) tweeting annoyingly/poorly about Y.
-
-
I don't see how machine learning would help here. These things can't be automated -- human judgment (from poster and recipient) is required.
-
Simple architecture: train on likes and RTs and filter by that. Leave poster side alone. If they rant into void and nobody hears, net good
End of conversation
New conversation -
-
-
BTW, have you checked out Toutiao? If it's as good as reports indicate, I'd adjust my belief that we can "machine learning our way out of the problem" positively.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.