Bits

kenh giai tri | summer school honolulu |

Taking a Chance on Love, and Algorithms

By JENNA WORTHAM

Published: April 7, 2012

• Sign In to E-Mail
• Print
• Reprints

THE invitation from Yoke.me , a new online dating start-up, seemed innocuous enough. It suggested that I meet some of the single pals of one of my friends.

Enlarge This Image

Lloyd Miller

Yoke.me pulled in data from Facebook — my city, for example, and what movies I prefer — then generated matches with people from my extended social circle, based on common interests, like a shared love of Rihanna's music or "Game of Thrones."

It is ingenious, in a way. How many single people have trolled through a friend's photo album on Facebook, spotted someone cute and then asked for intel about his or her availability? Poring through a trove of friends of friends can seem better than gauging whether the creep factor of a random person is low enough to warrant an in-person meeting.

Yet the idea was still troubling. My friends and I started a long e-mail thread about it, riffing that despite its elegant design, it seemed awkward and presumptuous. Not all Facebook "friends" are actually friends, and it's not entirely clear that the bands and shows we've "liked" on Facebook can really be used to say anything meaningful about us.

"I've found my newest nightmare," one friend said. "One match was a girl because we share a birthday," said another. "One match was a guy because we both like Gilt," a shopping site. "Is this for finding friends, dates or enemies?"

To be fair, the problem doesn't seem to be confined to Yoke.me . It may be part of online dating itself. Sites and apps like OKCupid , eHarmony , Skout , Plenty of Fish and Match.com have attracted loyal followings. But in a world where we can pay someone for lunch by tapping two phones together and stream live television over a tablet computer, the de facto model of browsing through static profiles on a Web site or in a mobile app can feel comically outdated.

It may not be a problem that software can solve on its own, said Eli Finkel, a professor of social psychology at Northwestern University. "Technology is not the way to figure out who is compatible and will never be," he said. "At the end of the day, the human algorithm — neural tissue in our cranium called a brain — has evolved over a long period of time to size up people efficiently. On a blind date, a person arrives and in that instant I can say I'm glad I did this or regret it."

Professor Finkel, along with several other researchers, published a study this year raising doubts about the idea that a personality test or algorithm of the kind popularized on eHarmony, can help you meet a potential mate.

Sites that say algorithms can help you find your soul mate "are probably spitting in the wind," said Harry Reis, a professor of psychology at the University of Rochester and a co-author of the algorithm paper, who has written upwards of 120 papers on online dating.

EHarmony counters that the algorithms it uses do work, citing research it conducted investigating the satisfaction of couples who met through the site, and their divorce rate.

The system that eHarmony has built is "based on years of empirical and clinical research on married couples," said Becky Teraoka, an eHarmony spokeswoman. They include "aspects of personality, values and interest, and how pairs match on them, that are most predictive of relationship satisfaction."

While Professors Finkel and Reis question the value of algorithms, they do say that online dating is useful because it can broaden the pool of people you come across on a regular basis.

"In everyday life you don't encounter people with signs on their head that say, 'I'm single and looking,' " Professor Reis said. On sites you can find "dozens of people that you might want to meet."

The trick is to weed out the weirdos and arrange a face-to-face meeting as quickly as possible — which, in a sense, is what Yoke.me is trying to do, as are similar services like theComplete.me and Coffee Meets Bagel .

Other sites are trying to move past the algorithm. A start-up called myMatchmaker uses in-the-flesh people as intermediaries. Some, like Nerve.com, and How About We , aim to streamline the process and encourage interactions around more than a profile.

But Kevin Slavin, a game developer who studies algorithms, says those sites are already starting from a flawed base.

The digital personas we cultivate on Facebook are often not very indicative of who we are, he said. "A first date is the most tangible instance of you being the best possible version of yourself, the version you think will be the most attractive to someone else," he said. "It is impossible for that to be the same person on Facebook."

Rob Fishman, who helmed the development of Yoke.me , says he views the service as an icebreaker, not as a crystal ball capable of divining whether or not someone is your one true love. "We aren't saying you will want to spend your life together; you don't even know each other yet," he said. "You like the same band, talk amongst yourselves."

Eventually, Mr. Fishman said, the service will be sophisticated enough to incorporate real-time data funneled through Facebook about songs people are listening to and articles they are reading and to make matches based on that — perhaps a more realistic way to connect two people through a social network.

ALL of this may simply mean that online dating is at an early stage. In other realms, we're already moving toward a future when the most dazzling and successful technologies are not visible and work almost by magic.

Consider Kinect from Microsoft. You can play a dance game by moving your whole body, without the need to hold a physical controller. Or try Square's latest mobile application, Pay With Square . The app's software will show a cashier a photo of a customer to verify payment information. Shoppers never even have to remove their phones from their pockets — only say their names and show their faces.

Then there is the Paper drawing app for the iPad . Its "rewind" feature lets users twist two fingers in a counterclockwise motion to erase their last few brushstrokes.

And, of course, there is Siri, the iPhone service that can understand spoken commands, perform Web searches and write and send text messages. Although Siri isn't perfect, it feels like a taste of the future.

That shift is leaving online dating in the dust. It feels clunkier than it should — like a poorly designed tablet or a Web service that keeps crashing.

It's a technology quandary fit for modern times, and one that doesn't have a clear solution in sight — yet. No one wants to see Cupid interfering with his or her love life; we just want the arrow to hit squarely on its mark. And, maybe someday, it will.

Theo www.nytimes.com