The perspectives toxicity API is a severely flawed outcome that shouldn’t ship. Not in this state.https://twitter.com/violetblue/status/903697800226979840 …
-
-
I doubt it'd be able to handle context-dependent stuff (like sarcasm) effectively, still
-
text is the wrong thing to be looking at, you want embedding vectors from the social graph
-
I should clarify: 100% accurate at categorizing a user given access to all their posts. Not necessarily at classifying one post.
-
only for casual harassment, maybe. definitely not for organized griefing
-
if you create an account for the sole purpose of greifing you can control the context
End of conversation
New conversation -
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.