@PsychRabble Some pretty cool evidence of stereotype accuracy in this paper, and some funny PC quotes you can use for upcoming papers that complain about leftism embedded in research language use. <-- Someone should show this quantitatively using machine learning!
-
-
Show this thread
-
E.g. this one is particularly obvious. Word embeddings across datasets highly correlated, and correlates pretty well with ratings by human subjects from MTurk. Still, they don't use the chance to calculate the actual accuracy using known distributions of professions! Why?pic.twitter.com/XfPJqtvbMa
Show this thread
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.