Facial recognition technology can accurately predict person's political beliefs: Study

A recent study published in Scientific Reports revealed that facial recognition technology can accurately predict someone’s political stance from ir Facebook profile photo. According to study, authored by Michal Kosinski, algorithm shows greater accuracy in deducing a person’s political orientation than eir human judgement or a personality test. A common facial recognition algorithm was applied to images of more than a million individuals drawn from ir entries on social media platform to predict ir political orientation by comparing ir similarity to faces of liberal and conservative ors. 

Kosinski, who is an associate professor at Stanford University, said that he has been studying privacy risks over algorithms over last dece. While speaking to PsyPost, he said that companies collect data and develop algorithms aimed at extracting insights, but are reluctant to reveal how accurate such models are. Kosinski ded that facial technology can accurately expose traits ranging from sexual orientation to personality. 

RE: Starlink Internet May Not Work Properly In India; Here's Why

Kosinski’s study applied a facial recognition algorithm to nearly 1,085,795 faces. Of this dataset, 977,777 came from dating website users in US, UK and Cana who h self-reported ir political orientation. or 108,018 faces were from Facebook users in US who h also self-reported ir political orientation and ditionally completed a 100-item personality test. 

algorithm n compared each participant’s facial features to average facial features of liberals and conservatives. As per study, technology used se similarity measurements to determine likelihood that a participant was eir a conservative or a liberal. result showed that algorithm was able to predict political orientation alarmingly well and with similar accuracy across countries and social media platforms. 

RE: Microsoft Says Chinese Hackers Remotely Plundering Email Inboxes

Accuracy over 70%

study said that among US Facebook users, this accuracy hit 73 per cent and among US dating website users, accuracy was 72 per cent. Among dating website users in UK and Cana, accuracy reached 70 per cent and 71 per cent respectively. author of study noted that algorithm performed substantially better than humans, who are only able to distinguish between a liberal and conservative with 55 per cent accuracy. 

Furr, study revealed that political orientation is linked to certain demographic traits that can be easily observed in face. researcher even explored wher certain features were tied to political orientation, including facial expression, eyewear, facial hair and he pose. Kosinski found that he orientation showed 58 per cent predictive power, with Liberals being more likely to face camera directly. study noted that emotional expression h 57 per cent predictive power, with Liberals being more likely to show surprise and less likely to show disgust. Kosinski said that his findings likely underestimate intelligence of such technology, furr ding that a higher accuracy would likely be revealed with higher resolution images, multiple images per person, or an algorithm specifically built for identifying political orientation.

(Image: @docrussjackson/Twitter)

RE: Google Updating Its Productivity Software To Meet Needs Of Remote Workers Amid COVID-19

RE: What Happened To Orby TV Service? Was Orby TV Out Of Business?