I thought Twitter had introduced a new feature to hide replies when it detected that people were just piling on without saying anything substantial. Pretty clever, I thought. But it turned out I'd just muted the conversation without realizing it.
-
I have been wondering if there are good "substantial" detectors out there yet.
I would guess that existing text classifiers are good enough, if you trained one on corpora of each kind of reply.
-
-
My last two ycombinator posts had 622 upvotes, then I was shadow-banned (logging in shows my post as “new” but no one else can see it). How do you feel about that?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Telling between actual content and unsubstantiated fluff is actually a pretty good research topic! If any grad students are reading this. ;)
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.