A.I. can predict your future tweets by looking at your friends’ accounts
A new study shows how machine-learning methods could examine your friends' past tweets to accurately predict your future behavior online.
- The study examined the past tweets of hundreds of Twitter users, each within a particular social circle, in order to see how accurate of predictions it's possible to make with machine-learning techniques.
- The results showed that machine-learning techniques can predict the future Twitter activity of a given user by looking only at about 9 of their friends, and that these predictions are about as accurate as predictions made with the benefit of looking at the user's past writings.
- The findings have troubling implications for online privacy, namely that, in theory, not even leaving Facebook or Twitter would prevent someone from generating an accurate profile of you.
It's probably not much of a surprise to know it's possible to take all of your past writings from Twitter, have a computer examine them, and then have it make a pretty accurate prediction about the types of content you're likely to write in the future. What's more surprising, however, is what a new study shows: It's possible for an A.I. to accurately predict someone's Twitter activity by looking only at the online behavior of a handful of that person's friends.
The results highlight a troubling implication: Not even deleting your Twitter or Facebook account would theoretically prevent someone from developing a profile on you — one that, as the study suggests, could be quite accurate:
"The ability of a machine learning method to accurately profile individuals from their online traces is reflected in the predictability of their written text."
The study, published in the journal Nature Human Behavior, was designed to find out just how accurate of predictions it's theoretically possible for machine-learning methods to make about a person's future social media activity by using data on people within their social network.
"We used some very interesting mathematics from information theory to say: If you had the perfect machine learning method, how well could you do?" lead author James Bagrow, a data scientist at the University of Vermont, told Science Magazine.
Here's a summary of how a machine-learning technique would make such predictions, as the study authors wrote:
The ability of a machine learning method to accurately profile individuals from their online traces is reflected in the predictability of their written text. Indeed, with a language model trained to predict the words a user will post online, in principle, one can construct a profile of the user by evaluating the likelihoods of various words to be posted, such as terms related to politics. Thus, quantifying the predictive information contained within a user's text allows us to understand the potential accuracy such methods can potentially achieve given a user's data.
For the study, the researchers looked at more than 30 million posts from about 13,900 Twitter users, each of whom had 50 to 500 followers. From these data sets they designated 927 so-called ego networks, at the center of which was a Twitter user and about 9 of their most frequently mentioned Twitter contacts. The researchers then looked at all of the users' past writings, categorizing them based on the contents and timings of the tweets, finding that users typically only used between 45 and 256 different words to compose tweets, which is "far smaller than the typical user's ~5,000-word vocabulary," the authors wrote. This limited range makes it relatively easy to predict words users are likely to write.
After conducting various tests, the results showed that machine-learning techniques could achieve 95% potential predictive accuracy for a given person using their social ties alone, without examining that individual's personal Twitter data. Although the study didn't actually predict specific tweets, the study illustrates the striking amount of predictive information about us that lies within our social groups.
One interesting note about the findings: Generally, when researchers were gauging the potential predictive accuracy for a given user, the accuracy increased as they added more friends of the user to the mathematical mix. But at a certain point, adding new friends stopped increasing accuracy. Interestingly, the authors wrote that this limit seems compatible with Dunbar's number, which describes how human beings can generally only maintain about 150 social ties. Or, as Dunbar explained, it's "the number of people you would not feel embarrassed about joining uninvited for a drink if you happened to bump into them in a bar."
In online privacy, your friends have control over your data
In an age when many are already worried about the lack of control they wield over their personal data, the study implies that even total control over our own data might be irrelevant if an organization can build an accurate profile of you by using your friends' data alone. In other words, even leaving Facebook or Twitter theoretically wouldn't prevent someone gathering reliable information about your political leanings, consumer habits, religious beliefs, etc.
"There's no place to hide in a social network," Lewis Mitchell, a co-author on the new study, told The University of Vermont's UVM Today.
Another implication: When you make your data accessible, you're also potentially exposing the data of those to whom you're connected, as Bagrow told Science Magazine:
"When they give up their own data, they're also giving up data on their friends," Bagrow said. "What we think is an individual choice in a social network is not really."
Of course, some people's online activity is harder to predict than others, and Twitter may prove to be a unique platform in terms of the ability for machine-learning techniques to predict behavior. Still, as long as it's possible to make such predictions, it's not hard to see how platforms like Twitter could, either unwittingly or negligently, cause damage by using this kind of information to expand its product, as the authors wrote:
"Language models derived in this way can have important consequences: combining predictions from a language model with an algorithm for recommending new social ties, for example, has the potential to create or exacerbate filter bubbles."
What would happen if you tripled the US population? Join Matthew Yglesias and Charles Duhigg at 1pm ET on Monday, September 28.
Whether or not women think beards are sexy has to do with "moral disgust"
- A new study found that women perceive men with facial hair to be more attractive as well as physically and socially dominant.
- Women tend to associate more masculine faces with physical strength, social assertiveness, and formidability.
- Women who display higher levels of "moral disgust," or feelings of repugnance toward taboo behaviors, are more likely to prefer hairy faces.
Beards and perceptions of masculinity<img type="lazy-image" data-runner-src="https://assets.rebelmouse.io/eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpbWFnZSI6Imh0dHBzOi8vYXNzZXRzLnJibC5tcy8yMjU5OTg0MC9vcmlnaW4uanBnIiwiZXhwaXJlc19hdCI6MTY0NzkxMjM3N30.cH-GqNwP5GVqvstgJWAhBPn1B_lYpVEAI0I7iax7EQw/img.jpg?width=1245&coordinates=0%2C1900%2C0%2C849&height=700" id="caae6" class="rm-shortcode" data-rm-shortcode-id="cb0a355a4e8e1899789bc45f3f7aef56" data-rm-shortcode-name="rebelmouse-image" />
Photo Credit: Wikimedia<p>The study used 919 American (mostly white) women ages 18-70 who rated 30 pictures of men they were shown with various stages of facial hair growth. The photographs depicted men with faces that had been digitally altered to look more feminine or more masculine, with a beard and without a beard. The women rated the men according to perceived attractiveness for long-term and short-term relationships. The study found that the more facial hair the men had, the higher the men were rated on their attractiveness, particularly for their suitability for a long-term relationship.</p><p>Part of this might be attributed to facial masculinity — i.e. protruding brow ridge, wide cheekbones, thick jawline, and deeply set narrow eyes — which conveys information to a woman about a man's underlying health and formidability. Women tend to associate more masculine faces with physical strength and social assertiveness. It can also indicate a man with a superior immune response. The researchers suggested that their findings favoring bearded men could be due to the fact that facial hair enhances the masculine facial features on a man's face, like creating the illusion of a thicker jaw line. This could communicate direct benefits to women like resources and protection that would enhance survival among mothers and their infants. In other words, while a beard doesn't mean superior genetics in and of itself, it might be a primitive, ornamental way of saying, "Hey girl, I'm a testosterone-fueled lean, mean, pathogen fighting machine." <br></p><p>It could also be that a beard becomes its own destiny. The researchers in this study cite prior research that found that by growing a beard, men felt more masculine and had higher levels of serum testosterone, which was linked to a higher level of social dominance. They also tended to subscribe to more old-school beliefs about gender roles in their relationships with women as compared to men with clean-shaven faces.<span></span><br></p>
What does disgust have to do with beard preference?<p>Obviously, not all women dig beards. The researchers were particularly interested in what traits make a women prefer bearded men over clean-shaven faces. They looked into several factors including a woman's disgust levels on various concepts, her desire to become pregnant, and her exposure to facial hair in her personal life. </p><p>According to the study, women who were not into facial hair were turned-off by potential parasites or other critters they imagined could be in the hair or skin. Women ranking high on this "ectoparasite disgust" scale might have viewed beards as a sign of poor grooming habits. However, women who ranked higher in levels of "pathogen" did find the bearded men to be desirable, possibly because they perceived beards as a signal of good health and immune function. An intriguing discovery in the study was links to morality. Women who displayed higher levels of "moral disgust," or feelings of repugnance toward taboo behaviors, were more likely to prefer hairy faces. The authors opined that this could reflect a link between beardedness, politically conservative outlooks, and traditional views regarding performances of masculinity in heterosexual relationships.</p>
Additional findings<img type="lazy-image" data-runner-src="https://assets.rebelmouse.io/eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpbWFnZSI6Imh0dHBzOi8vYXNzZXRzLnJibC5tcy8yMjU5OTg1My9vcmlnaW4uZ2lmIiwiZXhwaXJlc19hdCI6MTYyNDI1NjUyOX0.P9B8WbmJR0q4nfzYZKbuNSA-2SAigVWJgrQE-_Gxlds/img.gif?width=980" id="49143" class="rm-shortcode" data-rm-shortcode-id="2ed3b1d6f20fc170bf2974646e565e8d" data-rm-shortcode-name="rebelmouse-image" />Giphy<p>The correlations that existed between married and single women's rating on the attractiveness of beards were not particularly clear, although the researchers noted that single and married women who wanted children tended to find beards more attractive than the women who didn't want children. They also found that women with bearded husbands found beards to be more attractive, which might indicate that social exposure to beards influences how desirable they are perceived of as being. Or it could be that men with wives who like beards grow beards.</p><p>It's important to note that culture plays a huge role in how attractive women perceive certain male characteristics as being. This study looked at a small, culturally specific group of American women, so no big, universal claims should be made about masculinity, facial hair, and male desirability to women. However, research like this is important in highlighting how human grooming decisions are driven by much more than fashion trends. Sociobiological, economic, and ecological factors all play a part in the way we choose to present ourselves.</p>
Dominique Crenn, the only female chef in America with three Michelin stars, joins Big Think Live.
Having been exposed to mavericks in the French culinary world at a young age, three-star Michelin chef Dominique Crenn made it her mission to cook in a way that is not only delicious and elegant, but also expressive, memorable, and true to her experience.
New experiments find weird quantum activity in supercold gas.
Quantum Mechanics, Onions, and a Theory of Everything<span style="display:block;position:relative;padding-top:56.25%;" class="rm-shortcode" data-rm-shortcode-id="036ae7b8dd661df2d125a3421a0299ba"><iframe type="lazy-iframe" data-runner-src="https://www.youtube.com/embed/bcVruA0AJ-o?rel=0" width="100%" height="auto" frameborder="0" scrolling="no" style="position:absolute;top:0;left:0;width:100%;height:100%;"></iframe></span>
Researchers say that moral self-licensing occurs "because good deeds make people feel secure in their moral self-regard."
Books about race and anti-racism have dominated bestseller lists in the past few months, bringing to prominence authors including Ibram Kendi, Ijeoma Oluo, Reni Eddo-Lodge, and Robin DiAngelo.