How we did it
Through special custom software we collected data from more than 1,000,000 Facebook users. What we collected is their "public data" - some of their personal data (name, country, Facebook groups they subscribe to) plus their main profile picture and a few friend relationships.
We built a database with all this data, then began to analyze the pictures that showed smiling faces. The vast majority of pictures were both amateurish and somehow almost involuntarily or unconsciously alluring. And they are almost always "smiling".
It's also evident that the majority of users want to appear in the best shape and look. They are acting on Facebook’s mandatory mechanism: establish new relationships. Facebook is based on the voluntary uploading of personal data and sharing it with friends. The more friends the better. Being personal and popular a Facebook user is exposing him/herself to many others, continuing to establish new relationships.
Once the database was ready, we studied and customized a face recognition algorithm. The algorithm used self learning neural networks and was programmed to "group" the huge amount of faces we collected (and their attached data) in a few simple categories. The categories are among the most popular that we usually use to define a person at a distance, without knowing him/her, or judging based only on a few behaviors. We picked six categories ("climber", "easy going", "funny", "mild", "sly" and "smug" - working definitions), with some intuitive differences, for both male and female subjects.
The software effectively extracted 250,000 faces that were connected to the relevant public data in our database.
After grouping them, we started to dive into these seas of faces, with all the perceptual consequences. And we started to think about why we felt so overwhelmed.
In "The Love Delusion" essay, Dan Jones cites Martie Haselton’s research, which indicates that men typically overestimate the sexual interest conveyed by a woman's smile or laughter. When men see someone of the opposite sex smile at them they tend to think "she must be interested." By the way, women simply see a smile. [Dan Jones "The Love Delusion", March 31 2007, New Scientist]. Further, Heather Rupp, a graduate student at Emory University in Atlanta completed a study about the difference between the reactions of women and men when looking at the same erotic images. Tracking the eye movements of study participants "the big surprise was that men looked at the faces much more than women did."
Dr. Kim Wallen (who directs the lab where this experiment was performed) suggested that men scrutinize faces in pornographic imagery because a man often looks to a woman's face for cues to her level of sexual arousal, since her body, unlike a man's, does not give her away.
So the role of the face in establishing a potentially intimate relationship is stronger than generally thought. And this is also at the base of Facebook’s social system. A Facebook user is supposed to have increasing numbers of friends, but the website can also be used to actively look for a new relationship, by exploiting the illusory capital of accumulated relationships, signified by switching (mentally or often practically) into the "single" (i.e. available) status.
In "The Social Network" movie Jessie Eisenberg/Mark Zuckerberg becomes more and more excited as the concept of Facebook gets refined and he lets it be known that "I'm not talking about a dating website". Facebook is not a dating website, but it works using the same triggering principles. And for a few million of its "500 million active users" it does become a dating website.
So by combining all this information we wanted to make this further step easier for everybody.
We established a dating website [www.Lovely-Faces.com], importing all the 250,000 profiles. This step builds the virtual land that Facebook is always close to but never explicitly steps in, being just an enormous background to the active process of searching for potential sexual relationships.
The profiles will be definitively "single" and available, in a fairly competitive environment, with real data and real faces that users have personally posted. Their smiles will finally reach what they unconsciously really want: more relationships with unknown people, attracted by their virtual presence.
The price users pay is being categorized as what they really are, or better, how they choose to be represented in the most famous and crowded online environment. The project starts to dismantle the trust that 500 million people have put in Facebook.
The project talks about the consequences of posting sensitive personal data on social network platforms, and especially the consequences in real life. These consequences are always underestimated because we still instinctively tend to confine what we do online in the visual space of the screen. Face-to-facebook practically questions online privacy through one of the web’s most iconic platforms. And as with GWEI and Amazon Noir we're not just making a sophisticated critical action against another giant online corporation, but we are also trying to formulate a simple hack that everybody can potentially use.
Everybody can steal personal data and re-contextualize it in a completely unexpected context.
And that shows, once more, how fragile and potentially manipulable the online environment actually is.