A View from Emerging Technology from the arXiv
Psychologists Use Social Networking Behavior to Predict Personality Type
The ability to automatically determine personality type could change the way social networks target services to users
One of the foundations of modern psychology is that human personality can be described in terms of five different forms of behavior. These are:
1. Agreeableness–being helpful, cooperative and sympathetic towards others
2. Conscientiousness–being disciplined, organized and achievement-oriented
3. Extraversion–having a higher degree of sociability, assertiveness and talkativeness
4. Neuroticism–the degree of emotional stability, impulse control and anxiety
5. Openness–having a strong intellectual curiosity and a preference for novelty and variety
Psychologists have spent much time and many years developing tests that can classify people according to these criteria.
Today, Shuotian Bai at the Graduate University of Chinese Academy of Sciences in Beijing and a couple of buddies say they have developed an online version of the test that can determine an individual’s personality traits from their behavior on a social network such as Facebook or Renren, an increasingly popular Chinese competitor.
Their method is relatively simple. These guys asked just over 200 Chinese students with Renren accounts to complete online, a standard personality test called the Big Five Inventory, which was developed at the University of California, Berkeley during the 1990s.
At the same time, these guys analyzed the Renren pages of each student, recording their age and sex and various aspects of their online behavior such as the frequency of their blog posts as well as the emotional content of the posts such as whether angry, funny or surprised and so on.
Finally, they used various number crunching techniques to reveal correlations between the results of the personality tests and the online behavior.
It turns out, they say, that various online behaviors are a good indicator of personality type. For example, conscientious people are more likely to post asking for help such as a location or e-mail address; a sign of extroversion is an increased use of emoticons; the frequency of status updates correlates with openness; and a measure of neuroticism is the rate at which blog posts attract angry comments.
Based on these correlations, these guys say they can automatically predict personality type simply by looking at an individual’s social network statistics.
That could be extremely useful for social networks. Shuotian and comapny point out that a network might use this to recommend specific services. They give the rather naive example of an outgoing user who may prefer international news and like to make friends with others.
Other scenarios are at least as likely. For example, such an approach might help to improve recommender systems in general. Perhaps people who share similar personality characteristics are more likely to share similar tastes in books, films or each other.
There is also the obvious prospect that social networks would use this data for commercial gain; to target specific adverts to users for example. And finally there is the worry that such a technique could be used to identify vulnerable individuals who might be most susceptible to nefarious persuasion.
Ethics aside, there are also certain questions marks over the result. One important caveat is how people’s response to psychology studies online differs from those done at other times. That could clearly introduce some bias. Then there are the more general questions of how online and offline behaviours differs and how these tests vary across cultures. These are things that Shuotian and Co. want to study in the future.
In the meantime, it is becoming increasingly clear that the data associated with our online behavior is a rich and valuable source of information about our innermost natures.
Ref: arxiv.org/abs/1204.4809: Big-Five Personality Prediction Based on User Behaviors at Social Network Sites
Meet the Experts in AI, Robotics and the Economy at EmTech Next.Learn more and register