FB pixel

AI researchers say personality judgments can be made based on photographs

Categories Biometric R&D  |  Biometrics News
AI researchers say personality judgments can be made based on photographs
 

Scientists from two Moscow universities, the National Research University Higher School of Economics (HSE), and the Open University for the Humanities and Economics, said in a new paper, Assessing the Big Five Personality Traits Using Real-Life Static Facial Images, published in Scientific Reports, that “there is ample evidence that morphological and social cues in a human face provide signals of human personality and behavior,” and that “previous studies have discovered associations between the features of artificial composite facial images and attributions of personality traits by human experts.”

The researchers have teamed up with the Russian-British start-up BestFitMe to program artificial neural networks to make trustworthy personality judgments based on static photographs of human faces.

The researchers, Alexander Kachur, Evgeny Osin, Denis Davydov, Konstantin Shutilov and Alexey Novokshonov presented what they said are “new findings demonstrating the statistically significant prediction of a wider set of personality features (all the Big Five personality traits) for both men and women using real-life static facial images.”

The five scientists reported that “volunteer participants provided their face photographs (31,367 images) and completed a self-report measure of the Big Five traits,” and that they then “trained a cascade of artificial neural networks (ANNs) on a large labelled dataset to predict self-reported Big Five scores. The highest correlations between observed and predicted personality scores were found for conscientiousness (0.360 for men and 0.335 for women) and the mean effect size was 0.243, exceeding the results obtained in prior studies using ‘selfies.’”

“The findings strongly support the possibility of predicting multidimensional personality profiles from static facial images using ANNs trained on large labelled datasets,” the researchers said, explaining that “future research could investigate the relative contribution of morphological features of the face and other characteristics of facial images to predicting personality.”

Their findings, if they can be replicated, would indicate that AI can make accurate guesstimates about the comparative self-repute of two indiscriminately selected individuals on a personality feature in 58 percent of cases in contrast to the 50 percent that would be expected by mere chance, indicating an artificial neural network interpreting static facial images surpasses the ability of a human tasked with determining a target person’s traits in person without having even met the person.

According to the scientists, numerous studies have already “linked facial images to personality,” and that it has “been established that humans are able to perceive certain personality traits from each other’s faces with some degree of accuracy. In addition to emotional expressions and other nonverbal behaviors conveying information about one’s psychological processes through the face, research has found that valid inferences about personality characteristics can even be made based on static images of the face with a neutral expression.”

“These findings,” the researchers assert, are able to “suggest that people may use signals from each other’s faces to adjust the ways they communicate, depending on the emotional reactions and perceived personality of the interlocutor.” They referred to studies they said focused “on the objective characteristics of human faces [which] found some associations between facial morphology and personality features. For instance, facial symmetry predicts extraversion.”

“Another widely studied indicator is the facial width to height ratio (fWHR), which has been linked to various traits such as achievement striving, deception, dominance, aggressiveness, and risk-taking.”

However, they noted, “Such signals must be fairly informative and sufficiently repetitive for recipients to take advantage of the information being conveyed.”

“There are several theoretical reasons to expect associations between facial images and personality,” the researchers explained. “First, genetic background contributes to both face and personality,” and that genetics somehow “correlates [to] craniofacial characteristics” which they stated “have been discovered both in clinical contexts and in non-clinical populations. In addition to shaping the face, genes also play a role in the development of various personality traits, such as risky behavior, and the contribution of genes to some traits exceeds the contribution of environmental factors.”

Secondly, they reported, “there is some evidence showing that pre- and postnatal hormones affect both facial shape and personality. For instance, the face is a visible indicator of the levels of sex hormones, such as testosterone and oestrogen, which affect the formation of skull bones and the fWHR. Given that prenatal and postnatal sex hormone levels do influence behavior, facial features may correlate with hormonally driven personality characteristics, such as aggressiveness, competitiveness, and dominance, at least for men. Thus, in addition to genes, the associations of facial features with behavioral tendencies may also be explained by androgens and potentially other hormones affecting both face and behavior.”

The scientists further reported that “the perception of one’s facial features by oneself and by others influences one’s subsequent behavior and personality. Just as the perceived ‘cleverness’ of an individual may lead to higher educational attainment, prejudice associated with the shape of one’s face may lead to the development of maladaptive personality characteristics (i.e., the ‘Quasimodo complex’). The associations between appearance and personality over the lifespan have been explored in longitudinal observational studies, providing evidence of ‘self-fulfilling prophecy’-type and ‘self-defeating prophecy’-type effects.”

Finally, they noted, “some personality traits are associated with habitual patterns of emotionally expressive behavior.” For example, “habitual emotional expressions may shape the static features of the face, leading to the formation of wrinkles and/or the development of facial muscles.”

Conclusion, though, the researchers said, “a quick glance at the sizes of the effects found in [the studies they reviewed] reveals much controversy,” noting that “the results appear to be inconsistent across studies and hardly replicable. These inconsistencies may result from the use of small samples of stimulus faces, as well as from the vast differences in methodologies.”

The researchers therefore conclude that “stronger effect sizes are typically found in studies using composite facial images derived from groups of individuals with high and low scores on each of the Big Five dimensions,” and “the task of identifying traits using artificial images comprised of contrasting pairs with all other individual features eliminated or held constant appears to be relatively easy. This is in contrast to realistic situations, where faces of individuals reflect a full range of continuous personality characteristics embedded in a variety of individual facial features.”

Article Topics

 |   |   | 

Latest Biometrics News

 

ACCS announces participants in Australia’s Age Assurance Technology Trial

In keeping with its philosophy of transparency by default in running Australia’s Age Assurance Technology Trial, the Age Check Certification…

 

DPI-as-a-Packaged Solution marks major milestone with Trinidad and Tobago rollout

The first ever implementation of DaaS — DPI-as-a-Packaged Solution — is going live in Trinidad and Tobago in a test…

 

AI agents spark musings on identity, payments and wallets

AI agents continue to attract attention, including in the digital identity industry, which sees an opportunity for innovation. Their importance…

 

Trump deregulation is re-shaping the future of biometric surveillance in policing

The advent of AI has exponentially increased the capabilities of biometric tools such as facial recognition, fingerprint analysis, and voice…

 

World expands Android support for World ID credentials

World’s positive relationship with Malaysia continues, with the launch of Android support for World ID Credentials in the country, following…

 

Sri Lanka national data exchange to connect digital ID and public services

A fully developed foundational ID system, including citizen registration, may take 18 to 24 months for Sri Lanka to implement,…

Comments

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Most Viewed This Week

Featured Company

Biometrics Insight, Opinion

Digital ID In-Depth

Biometrics White Papers

Biometrics Events