In addition to being the worst, online dating is literally the fucking worst. Unless you have a thing for a very specific type of vulnerability, it's not so much a romance and fulfillment machine as it is a hybrid anxiety generator/saltlick for creeps. I have several close friends who ended up marrying people they met online, so web-based hump-sourcing is not completely devoid of utility, but in day-to-day practice that shit is mainly just a bunch of weirdos incessantly updating you on their horniness levels while you sit at home obsessing over whether or not your ears are mannish. Then, once in a blue moon, you "get" to go spend three hours with the least worst medium-okay person you can find, and once in a blue moon's blue moon you actually have an awesome time and make a new friend. The rest of it is torture.
That's why a team of computer scientists at the University of Iowa in Iowa City have tasked themselves with streamlining and hopefully improving the cost/benefit ratio of online dating. Existing compatibility engines only take into account shared interests and personality traits, as well as your stated physical preferences and what type of people you reach out to, but fail to factor in that je ne sais quoi that actually makes people attracted to one another. This new research seeks to quantify that unquantifiable spark, and their method is actually fairly straightforward.
The problem with this approach is that it takes no account of your attractiveness. If the people you contact never reply, then these recommendations are of little use.
So Zhao and co add another dimension to their recommendation engine. They also analyse the replies you receive and uses this to evaluate your attractiveness (or unattractiveness).
Obviously boys and girls who receive more replies are more attractive. When it takes this into account, it can recommend potential dates who not only match your taste but ones who are more likely to think you attractive and therefore to reply. "The model considers a user's "taste" in picking others and "attractiveness" in being picked by others," they say.
At least, that's the theory.
I don't necessarily think it's a given that people "who receive more replies are more attractive." They could also be desperately spamming everyone on every site and receiving tons of replies as a pure numbers game. They could be hearing back only from equally desperate people (or kind, open-minded people who like to give everyone a shot!—can you imagine?) who couldn't even give a shy fart about hotness. But even mutual desperation is its own form of attraction, I suppose.
I also don't personally believe that you can turn romance into a science, so online dating is always going to be a bit of a crapshoot. Unless you're the most knee-knockingly insecure PUA on earth, you've almost certainly experienced that startling, mind-expanding surprise-attraction to somebody you thought wasn't your "type." (In my opinion, the only reason to cling to "type" as a concept is subterranean self-confidence and a paralyzing fear of your own potential proclivities. There's safety in conformity.) So I hope systems like this—their focus, no doubt, tending toward traditional standards of attractiveness—don't wind up separating people even further from seemingly unconventional but potentially compatible partners.
But, that said, if it can adjust for all that and cut down on the number of "do u want do fuck boner" e-mails, I'm all for it. Someone needs to build a better mousetrap.