Human capital—encompassing cognitive skills and personality traits—is critical for labor market success, yet the personality component remains difficult to measure at scale. Leveraging advances in artificial intelligence and comprehensive LinkedIn data, we extract the Big 5 personality traits from facial images of 96,000 MBA graduates, and demonstrate that this novel" Photo Big 5" predicts school rank, compensation, job seniority, industry choice, job transitions, and career advancement. Using administrative records from top-tier MBA programs, we find that the Photo Big 5 exhibits only modest correlations with cognitive measures like GPA and standardized test scores, yet offers comparable incremental predictive power for labor outcomes. Unlike traditional survey-based personality measures, the Photo Big 5 is readily accessible and potentially less susceptible to manipulation, making it suitable for wide adoption in academic research and hiring processes. However, its use in labor market screening raises ethical concerns regarding statistical discrimination and individual autonomy.
I don’t have the time nor the expertise to read everything to understand how they take into account the bias that good looking white men with educated parents are way more likely to succeed at life.
Hi, Organizational Psychologist here who works in a lab alongside my personality Psych research supervisor. I have never heard of this method, never read this in any of the literature, and am genuinely disgusted anyone got ethics approval to run this study. The only way we use ML to evaluate personality is using natural language due to the tenants of the lexical hypothesis. I have never seen anyone attempt to create a big five measure from facial recognition nor have I ever heard of any theoretical models for personality based on faces…except for phrenology
I don’t have the time nor the expertise to read everything to understand how they take into account the bias that good looking white men with educated parents are way more likely to succeed at life.
i admittedly did not read the entire 61 pages but i read enough to answer this:
Lmao they source the photos from LinkedIn profiles. I’m sure that didn’t bias their training at all. Yes sir there’s no chance this thing is selecting for anything but facial features.
Edit: double lmao they’re all MBAs
Edit2: they didn’t even train the AI!! this paper is them just feeding linkedin photos into a third-party black-box API and then nodding thoughtfully at the results. i cant tell you how stupid the AI is because I can’t find any information about it or even the API mentioned in the paper.
Wow. When I saw the article I figured it would be bad, but that’s even worse than I expected lol
What is it with these idiots trying to re-brand racism and reinvent phrenology every few decades? Are they stupid enough to believe they’re the first to think of shit like this, or are they hoping we’re dumb enough to fall for it this time around?
![The Economist on using phrenology for hiring and lending decisions: "Some might argue that face-based analysis is more meritocratic" […] "For people without access to credit, that could be a blessing"](https://lemmy.ml/pictrs/image/14f5a0b4-82b6-498d-a689-36c2824dd296.png){kind=link}
I looked for the original article, abstract:
The PDF is downloadable here: https://scholar.google.com/citations?view_op=view_citation&hl=en&user=2eia4X4AAAAJ&sortby=pubdate&citation_for_view=2eia4X4AAAAJ%3A_FxGoFyzp5QC
I don’t have the time nor the expertise to read everything to understand how they take into account the bias that good looking white men with educated parents are way more likely to succeed at life.
Hi, Organizational Psychologist here who works in a lab alongside my personality Psych research supervisor. I have never heard of this method, never read this in any of the literature, and am genuinely disgusted anyone got ethics approval to run this study. The only way we use ML to evaluate personality is using natural language due to the tenants of the lexical hypothesis. I have never seen anyone attempt to create a big five measure from facial recognition nor have I ever heard of any theoretical models for personality based on faces…except for phrenology
one can also get the full paper directly from yale here without needing to solve a google captcha:
https://insights.som.yale.edu/sites/default/files/2025-01/AI Personality Extraction from Faces Labor Market Implications_0.pdf
i admittedly did not read the entire 61 pages but i read enough to answer this:
spoiler
they don’t
Lmao they source the photos from LinkedIn profiles. I’m sure that didn’t bias their training at all. Yes sir there’s no chance this thing is selecting for anything but facial features.
Edit: double lmao they’re all MBAs
Edit2: they didn’t even train the AI!! this paper is them just feeding linkedin photos into a third-party black-box API and then nodding thoughtfully at the results. i cant tell you how stupid the AI is because I can’t find any information about it or even the API mentioned in the paper.
Wow. When I saw the article I figured it would be bad, but that’s even worse than I expected lol
What is it with these idiots trying to re-brand racism and reinvent phrenology every few decades? Are they stupid enough to believe they’re the first to think of shit like this, or are they hoping we’re dumb enough to fall for it this time around?
They’re hoping they have sufficient cover with Nazis in the White House and they’re probably right.
How many times has Big 5 been debunked yet employers still like it for reasons?
I’m wondering if things like FAS (which can have certain facial characteristics) are muddling the results as well.