Live data from Hacker News

AI Model Detects Mental Disorders Based on Web Posts

home.dartmouth.edu

1–10 of 74 posts

Re: AI Model Detects Mental Disorders Based on Web Posts

#4
post #2

all it does is measure emotions... it's like saying if you're sad you must be depressed or if you're happy you must be manic

They are not measuring emotions in isolation; that would not be novel. They are computing signature patterns of emotional transitions. This is revealing of some mental disorders.

Re: AI Model Detects Mental Disorders Based on Web Posts

#5
I'd say very little good can come from this. What would be an example of an "appropriate" use of this technology?

Basically where it could excel is giving probabilistic prediction of "mental disorders" across a high volume of users. What is a good thing you would do with that? Advertising to suggest someone to get help, maybe?

Re: AI Model Detects Mental Disorders Based on Web Posts

#8

I'd say very little good can come from this. What would be an example of an "appropriate" use of this technology? Basically where it could excel is giving probabilistic prediction of "mental disorders" across a high volume of users. What is a good thing you would do with that? Advertising to suggest someone to get help, maybe?

I can see companies using this to screen applications to filter out potentially problematic people, sometimes with more social acceptability (think airline pilots), sometimes with less (most other jobs).

If you consider that "good" is another matter.

Re: AI Model Detects Mental Disorders Based on Web Posts

#9
post #3

Witty. But those claims must feel a bit insulting to people who actually study mental disorders, chemical imbalances etc.

"chemical imbalances", is that a thing?

I think so. A quick Google search returns 15.3M results. Googling for an exact match returns 217K results. All results seem to be related to mental health.

Re: AI Model Detects Mental Disorders Based on Web Posts

#10
post #3

Witty. But those claims must feel a bit insulting to people who actually study mental disorders, chemical imbalances etc.

I would say it is the same kind of bullshit. "Mental disorders" are just artificial conventions that classify emotional distress, non-compliant behavior and stuff.

There are no proven "chemical" imbalances with for example depression. And psychotropic medication does not balance the "chemicals".

I also doubt that being sad or mad about something on the internet will give you accurate predictions about the mental order or disorder of the user. Of course there will be some correlation, but there also will be a lot of false negatives and false positives. I mean diagnoses by non-artificial human professionals are quite unreliable.

Post reply on HN