Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AI Model Detects Mental Disorders Based on Web Posts

home.dartmouth.edu

Post reply on HN
Print view View original

31–40 of 74 posts

Re: AI Model Detects Mental Disorders Based on Web Posts

#31

Post by theothermelissa »

adg001 wrote: post #4
donkarma wrote: 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.

This was what stood out to me about the article as well. I could see something like this being a useful tool for therapists or self-help to be able to map the overall emotional tone of one's content over time.

Re: AI Model Detects Mental Disorders Based on Web Posts

#33

Post by scim-knox-twox »

dasyatidprime wrote: post #14
throwuxiytayq wrote: post #13

Earlier quoted context omitted.

Precisely. The cyber stalking of applicants is about to get even worse. Anyone having a public presence on social media is hurting themselves.

And anyone without one is then nobody.

Then I'm nobody and I'm good with that.

Re: AI Model Detects Mental Disorders Based on Web Posts

#34

Post by sdoering »

bogwog wrote: post #21
dasyatidprime wrote: post #14

Earlier quoted context omitted.

And anyone without one is then nobody.

Someone needs to build a bot that posts boring, but socially acceptable content that won’t raise any red flags for potential employers.

I disagree. I happily include my personal site with quite some controversial articles (being my opinion at that time) on it in my resume. It works as a great filter for companies I wouldn't want to work for.

Re: AI Model Detects Mental Disorders Based on Web Posts

#35

Post by protomyth »

I would assume that someone will come up with a phone app to fix text so it triggers no filters.

SaneSpeak fixes your communications to analyze as sane, honest, and confident. Simple sliders allow you to project the personality you want your audience's AI to pick up. Chose proven presets and watch those sales and promotions roll in.

Re: AI Model Detects Mental Disorders Based on Web Posts

#36

Post by pc86 »

bogwog wrote: post #21
dasyatidprime wrote: post #14

Earlier quoted context omitted.

And anyone without one is then nobody.

Someone needs to build a bot that posts boring, but socially acceptable content that won’t raise any red flags for potential employers.

Honestly you could probably train a GPT-3 based model on the posts of medium and high profile people in whatever industry you work in, add a couple post-content generation checks to eliminate any accidental plagiarism, and you'd be most of the way there.

Re: AI Model Detects Mental Disorders Based on Web Posts

#37

Post by pc86 »

sdoering wrote: post #34
bogwog wrote: post #21

Earlier quoted context omitted.

Someone needs to build a bot that posts boring, but socially acceptable content that won’t raise any red flags for potential employers.

I disagree. I happily include my personal site with quite some controversial articles (being my opinion at that time) on it in my resume. It works as a great filter for companies I wouldn't want to work for.

This works great for competent, experienced software engineers who are in extremely high demand right now. To be blunt, most people are not that valuable economically to a company, and so have to fight a lot more to get a lot less. Most people would find a hard time getting work with any broadly controversial topics associated with them.

There's also the argument that software engineers may not always be in such high demand, and you never know what's going to be catalogued and indexed to you 10, 20, 30 years from now.

Re: AI Model Detects Mental Disorders Based on Web Posts

#38

Post by dwaltrip »

afarviral wrote: post #6
mkl95 wrote: 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?

My understanding is that it has gone out of favor as a theory. It wasn’t ever developed into much of a robust model and is sorely lacking in many ways.

But this is a layman understanding so I could be missing something.

Re: AI Model Detects Mental Disorders Based on Web Posts

#39

Post by ada1981 »

mkl95 wrote: post #3

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

I’m fairly sure the “chemical imbalance” thing is still not a proven cause. It’s more of a metaphor psychiatrists use when trying to get someone to take meds.

Time in nature, meaningful work, healthy food, body movement, healthy relationships, processing emotional trauma, etc. are the contexts that ultimately get leverage on “mental health”.

For me, I was told by Standford psychiatrists I’d be on meds my entire life, presenting w suicidal depression, biploar, schizophrenia, anxiety,etc.

Thankfully I trusted my intuition and found a path through without traditional drugs (psychedelics helped).

But from my journey I realized “chemical imbalance” was more metaphor than reality… and sort of a hyphothesis that didn’t really play out.

Re: AI Model Detects Mental Disorders Based on Web Posts

#40

Post by mistrial9 »

flownoon wrote: post #20
version_five wrote: post #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?

Youre right that getting rates of mental disorders at the population level is a useful application. Checkout for example the hedonometer: https://hedonometer.org/timeseries/en_all/?from=2021-12-05&t... . People have also done population-level research showing that bad weather affect various seniment-based metrics of mental health: https://journals.plos.org/plosone/article?id=10.1371/journal...

> getting rates of mental disorders at the population level is a useful application

this post sounds dangerous to me -- there are vast differences in a legal judgement and a medical judgement; thirdly, political policy levers are sometimes used in ways that make very little sense, due to situational factors.

It is no secret that humans are competitive, tend towards violence, and political oppression exists to some extent, of some groups, almost everywhere. A "medical judgement" used for legal or worse, political purposes, I claim, is dangerous. The post above this one appears to make no distinctions and leans towards "yes, do this."

Post reply on HN