If you ever had the inkling that your presence on social media was giving away your game, you'd be absolutely correct. A Stanford behavioral professor says he has developed computer models to find links between social media users' online activity and their real-life personalities.
Big Data mining can be used to interrogate your social media 'shares' and 'likes' to predict whether your parents were divorced or not; whether you smoke, drink, or take drugs; your sexual orientation and more, says Dr. Michal Kosinski, an assistant professor in organizational behavior at Stanford Graduate School of Business.
Kosinski says computers can identify traits from a wide range of digital footprints.
"Broad measures, such as the number of your friends, number of your 'likes,' how many times you log in to Facebook, how many Tweets you have," when combined, can be a strong predictor of who you are, Kosinski said in an interview with Stanford News.
Computer Big Data
But it's only computer-based number crunching that provides the results. It's no good just manually going through a person's likes and dislikes, say, on Facebook, and making an assumption.
"Few Facebook 'likes' are so obviously linked with personality or other traits as to allow a human to use them in forming accurate judgments," he says.
However, when you include large amounts of that kind of data for computers to sift through, computers can decipher personalities.
"We humans, with our limited ability to simultaneously process more than a few facts at a time, are rather bad at it," he said in the article.
But if you allow a computer to combine large amounts of "subtle pieces of information," it can arrive at accurate predictions.
Years are important
I tried it, but there wasn't enough data in my Facebook account for the study's computer model to be able to figure me out at all. An insufficient number of my 'likes' matched with those in the database.
Possible cause: I don't use Facebook much, and Kosinski talks of using years of Facebook history in his analysis.
Of course, one big question would be: Can you fake it? The answer is probably not much. It's the years of data that contributes to the findings.
Those years of 'likes' and other social network interactions make it hard for people to misrepresent themselves, Kosinski thinks.
"It's easy for people to misrepresent themselves in, say, a half-hour-long interview or on a first date. It's much more difficult to monitor your appearances and opinions in years of your Facebook history," he said in the Stanford News interview.
But in any case, the manipulation of perception online is likely to be no different to the orchestration one creates in real life.
"We're just always involved in a lot of image control when we interact with others," he says.
Though, "in a way, Facebook and other social media might be conveying information that is closer to our true selves than what we reveal in a face-to-face interaction," he adds.
This article is published as part of the IDG Contributor Network. Want to Join?