Our social media profiles can provide some amazing insights into our personality. According to Jobvite’s 2014 Social Recruiting Survey, 55% of recruiters have reconsidered a candidate based on their social media profile.
A new study demonstrates just how insightful our online profiles can be: based on our Facebook, an algorithm can assess our personality more accurately than our friends.
What your Facebook account reveals about you
Previous research has examined two common social media red flags used by recruiters: (1) references and photos of alcohol and drug use and (2) badmouthing of superiors and coworkers. Results found:
- Extraversion: extraverted job candidates were more likely to post about alcohol and drugs.
- Agreeableness: disagreeable job candidates were more likely to badmouth their workplace.
Apparently, this is a no-no on Facebook.
A new study by Youyou and colleagues examined how accurately our Facebook Likes reflect our personality.
They looked at the Big Five personality traits (openness, conscientiousness, extraversion, agreeableness, and neuroticism) by collecting:
- Self-ratings of personality of 86,220 people
- Facebook Likes of 70,520 people
- Friend-ratings of personality of 17,622 people rated by one friend
- Friend-ratings of personality of 14,410 people rated by two friends
The researchers created computer models (algorithms) for predicting personality based on Facebook Likes.
Average accuracy of assessing personality
- 0.49 – Humans’ average accuracy
- 0.56 – Computers’ average accuracy
Number of Likes needed
- 100 – Likes for a computer to outperform a human on average
- 10 – Likes for a computer to outperform a colleague
- 70 – Likes for a computer to outperform a friend
- 150 – Likes for a computer to outperform a family member
- 300 – Likes for a computer to outperform a spouse
Why computers are more accurate than humans
The researchers explain that computers are more accurate than humans at assessing our personality for two main reasons:
- Information storage: Computers can retain and access an amount of information that would be extremely difficult, if not impossible, for a human to do.
- Data analysis: Computers use consistent algorithms that optimize accuracy whereas humans are affected by various cognitive and motivational biases.
This is why when it comes to making hiring decisions, algorithms are on average 50% more accurate than human instincts.
The “data revolution” happening in hiring and recruitment isn’t just hype: research has found that computers can be better judges of our personality than our friends. The researchers conclude
“In the future, people might abandon their own psychological judgments and rely on computers when making important life decisions…It is possible that such data-driven decisions will improve people’s lives.”
Instead of relying on inaccurate human judgment for important decisions like hiring, it’s time we embrace our trusty computer friends.
Latest posts by Ji-A Min (see all)
- People Analytics Software: Best Practices From The Experts - September 23, 2016
- Diversity Hiring: 6 Steps To Hiring More Diverse Candidates - September 22, 2016
- People Analytics For Recruitment: A How-To Pocket Guide - September 21, 2016