Re:Emotion Science Keeps Getting More Complicated. Can AI Ke...
by trevyn on Wednesday December 05, 2018 @02:44PM
(#18611741)
OCEAN is useful in predicting human behavior because there are certain common constellations of human behavior and disposition, and the meanings of the dimensions are easily understood by today’s humans. There certainly exists a more efficient representation, but machine-learned dimensions often don’t have easy analogues to existing human words.
Agreed that the DSM is kind of silly in that it draws arbitrary boundaries, but again, it’s pointing at common constellations of characteristics that are absolutely statistically predictive of behavior.
The underlying problem is that we are only just beginning to be able to formally represent complex behaviors in terms of underlying neural activity, and until we can do this fully and properly, there are still useful analyses that can be performed, they’re just “fuzzier”.
Agreed that the DSM is kind of silly in that it draws arbitrary boundaries, but again, it’s pointing at common constellations of characteristics that are absolutely statistically predictive of behavior.
The underlying problem is that we are only just beginning to be able to formally represent complex behaviors in terms of underlying neural activity, and until we can do this fully and properly, there are still useful analyses that can be performed, they’re just “fuzzier”.