This is very interesting. I expected to do better on the first one and I was so sure I'd failed the second. https://implicit.harvard.edu/implicit/takeatest.html …pic.twitter.com/du071q7JXV
-
So if you're not able to immediately unlearn being trainined one categorization and apply another, that indicates bias? I don't know.
The order of the two categorizations is randomized to account for that, and there's some compensation to account for the "unlearning".
-
-
To a large extent it's still a test for unlearning. And if it only evens out through average, telling individuals their "bias" is pointless.
-
Supposedly they've tested the impact of the ordering bias and found it to be rather small on an individual basis.
- Show replies
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.