Twitter's big QA problem after harassment is people who tweet well about X (and worth following for X) tweeting annoyingly/poorly about Y.
Conversation
Replying to
There are easy solutions for this (multiple tabs == multiple identities/feeds), but UX innovation for social tech is completely dead.
2
2
Replying to
I don't that will work. It's not a UX problem, more a machine learning problem to use interest graph to modulate social graph stream.
2
2
Replying to
I don't see how machine learning would help here. These things can't be automated -- human judgment (from poster and recipient) is required.
3
Replying to
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

