How You Move Your Phone Can Reveal Insights Into Your Personality (sciencealert.com) 56
schwit1 shares a report from ScienceAlert: It may sound strange at first, but a team of researchers in Australia has come up with a method to predict your personality traits using just the accelerometer in your phone. Well, that and your call and messaging activity logs. Also, the system works for some traits better than others. But it's an interesting take on how we may find connections through such seemingly unrelated things. In this case, we start at the Big Five personality traits. These have been used in psychology since the 1980's to help classify five dominant parts of our personalities. These five traits are extraversion (outgoing vs reserved), openness (curious vs cautious), neuroticism (confidence vs nervous), agreeableness (compassionate vs detached) and conscientiousness (organised vs easy-going).
The researchers analysed 52 people's phone habits between March 2010 and July 2011. Each participant was given a phone with sensing and collection software on it, which gave the researchers information on when and how much the phone was moving (accelerometer data), as well as the number and time of day of all calls and messages. The participants were also asked to complete a Big Five survey to score their personalities on the five traits. Then, the team also created a list of features related to the aspects of phone use they measured, that might potentially determine personality traits; for example, physical activity on weekend nights might predict extraversion, or the number of calls one makes might predict agreeableness. After crunching the numbers, the researchers found that some of the phone features really did predict some of the personality traits for the 52 participants. The phone data best predicted neuroticism, conscientiousness, and extraversion, but had trouble predicting the other two traits, especially openness. "There's also the issue of whether the team were actually looking at personality traits, or if the personality traits could be masked by other factors," the report adds. "For instance, neuroticism may be associated with different regularity of activity intensity in the night, however we cannot rule out many other possible explanations (e.g. neurotic people are more prone to stress and therefore - if this is the case, anyone with different personality traits that are stressed will still exhibit the same results)."
The study has been published in the journal Computer.
The researchers analysed 52 people's phone habits between March 2010 and July 2011. Each participant was given a phone with sensing and collection software on it, which gave the researchers information on when and how much the phone was moving (accelerometer data), as well as the number and time of day of all calls and messages. The participants were also asked to complete a Big Five survey to score their personalities on the five traits. Then, the team also created a list of features related to the aspects of phone use they measured, that might potentially determine personality traits; for example, physical activity on weekend nights might predict extraversion, or the number of calls one makes might predict agreeableness. After crunching the numbers, the researchers found that some of the phone features really did predict some of the personality traits for the 52 participants. The phone data best predicted neuroticism, conscientiousness, and extraversion, but had trouble predicting the other two traits, especially openness. "There's also the issue of whether the team were actually looking at personality traits, or if the personality traits could be masked by other factors," the report adds. "For instance, neuroticism may be associated with different regularity of activity intensity in the night, however we cannot rule out many other possible explanations (e.g. neurotic people are more prone to stress and therefore - if this is the case, anyone with different personality traits that are stressed will still exhibit the same results)."
The study has been published in the journal Computer.
Bring on the ads (Score:2)
You just know that we will all start getting ads now based on our personality types...
Re: (Score:3)
Great, does that mean I get ads for couch potatoes now? I barely move my phone when I'm at home, because it usually lies somewhere where I can't hear it so I don't get compelled to pick up when someone calls.
Re: (Score:2)
"Great, does that mean I get ads for couch potatoes now? I barely move my phone when I'm at home, because it usually lies somewhere where I can't hear it so I don't get compelled to pick up when someone calls."
Exactly. And those people who hold in their hand the whole day, because they don't have pockets, get ads for yoga pants. Those people are usually called 'girls'.
Re: (Score:2)
Nah, you'll probably just be lumped into the same category as me: Old farts who don't feel the urge to take a selfy of every log of shit they pass.
Comment removed (Score:5, Funny)
"Personality" (Score:5, Insightful)
That kind of "studies" ( The whole FIELD of personality "science") and the publicity it receives plays a big role in why psychology and psychologist as a whole have a terrible reputation. IMHO.
A shame because there are parts of psychology that could interest scientists like the study of cognitive biases.
An embarrassment to serious psychologists. But i have no doubt many business schools and marketers will buy it.
Re:"Personality" (Score:4, Informative)
Psychology is actually a lot more sane about personalities. There are box models but no serious psychologist will treat these as "one size fits all". They are well aware that a single individual will show vastly different traits depending on situation and context. The box models are useful as a means of communicating concepts, they are not labels to apply to individuals.
It's just that "it's complicated" isn't an answer that helps sell books or seminars, so labelling is exactly what self-help guru's do. The box models provide a whiff of legitimacy to their pseudo-science.
Re: (Score:1)
Until you get into the gender studies psychology staff. Then, your group membership as a victim, and your liberation from the bourgoise^H^H^H^H Western male patriarchy is the critical definition of your group, your oppression, and of yourself. You cannot possibly pass the class until you've taken on the identity of one of the approved victim classes and marched against the oppressive classes
If only I were making this stuff up. Take a very good look a the politics of the "gender studies" leaders, many of who
Re: (Score:1)
Re: (Score:2)
This is just Myers-Briggs crap again and is comprehensively derided by actual psychologists yet there are still plenty who buy into the extortionately priced snake oil peddled by team management "consultant" firms.
Re: (Score:1)
Definitely plausible, those 9G+ accelerations when it hits the floor could indicate anger issues.
Re:"Personality" (Score:5, Interesting)
The Big 5 model was the product of researchers approaching personality in a way more grounded in empiricism than a priori theories. The challenge is that human behavior is flexible and context-driven. Somebody you perceive as "lazy" may be quite energetic in situations you don't see him in. After decades of hotly contested research, the Big 5 are the last men standing; the only candidate traits out of dozens proposed that have consistent predictive power across multiple situations in every population studied.
It makes no sense to use deep learning and phone accelerometer data to figure out whether someone is "lazy", because your results are just reading the situations your subjects find themselves in. However, it *does* make to look for correlations with Big 5 traits. This doesn't mean this research will stand the test of time -- most research does not. But at least the question it is looking at means something.
Popular understanding of the field is still dominated by Freud and reactions to him, even though he is largely irrelevant these days to research and professional training. A lot of people can tell you their Myers-Briggs type, blissfully unaware that Myers-Briggs is built on Jungian psychoanalysis. Companies pay good money to have their employees classified with Myers-Briggs, even though it has never been empirically verified. The reason is something that anyone who's taken it will know: it's damned convincing.
In fact that's problem with personality tests, whether they're Myers-Briggs, Big 5, or Buzzfeed: they're inherently convincing. They ask you a bunch of questions and spit back a classification based on your answers. A psychological test based on a survey will never tell you anything about yourself that you don't already believe. This doesn't mean that it's necessarily useless, but if it's trying to parse a distinction that doesn't exist (e.g. whether you're a person who uses reason or feeling) it certainly is useless.
Re: (Score:1)
Re: (Score:2)
The Big 5 model was the product of researchers approaching personality in a way more grounded in empiricism than a priori theories.
So was phrenology [wikipedia.org] which tried to measure at a time when all other psychologists were busy with the soul (metaphysics). Yet it remains a pseudoscience.
"The only possible conclusion the social sciences can draw is: some do, some don't." -- Ernest Rutherford
Statistics 101 anyone? (Score:5, Insightful)
"some of the phone features really did predict some of the personality traits for the 52 participants"
I think you can drive a convoy of trucks through the holes in this statistical analysis. Sample size of 52, some features predict some personality traits. I wonder what would happen if they just mixed up whose phone is whose - I bet some features would have correlated with some personality traits too.
As for tracking physical activity, accelerator and times of messages will not tell you that someone is ziplining while their phone is left in the car.
Chair adds (Score:3)
Well, I shouted at my phone "fuck Google!" and tossed it out the window.
Then I started to get spam offering me chairs.
Go figure.
phone (Score:5, Funny)
"Each participant was given a phone with sensing and collection software on it"
aaah, you mean just a regular android phone.
I Hate the Entire Cellphone Market (Score:2)
A rather limited survey... (Score:1)
The information from an incredible 52 participants was analysed? We truly are in the age of big data.
Re: (Score:2)
Groundbreaking insight! (Score:2)
Some people leave the phone on their desk until it rings. Then they move it from the desk and hold it up to their ear during a conversation, leaving it there until the conversation ends. What personality trait does that activity indicate?
(Jeebus! Did someone actually pay for this study?)