Since it doesn’t rely on profile information, Zhao says it can also be used by other online services that match people, such as a job recruiting or college admissions.
Zhao’s study, “User recommendation in reciprocal and bipartite social networks—a case study of online dating,” was co-authored by Mo Yu of Penn State University and Bo Gao of Beijing Jiaotong University.
It looked at 475,000 initial contacts involving 47,000 users in two U. Zhao says the data suggests that only about 25 percent of those initial contacts were actually reciprocated.
Whether you’re looking for friendship, a random hookup or location-based love, there’s a slew of dating apps and websites out there for every kind of single. Formerly called “Bang with Friends,” this app lets you find friends on Facebook who are willing to get down tonight. Friends won’t know who’s selected them unless the feeling is mutual.
Grouper sets you up with a match, then lets both parties bring along two friends.
"If you think you’re not tech-savvy enough to download a dating app, think again," Laurie Davis, founder of e Flirt Expert and author of Love At First Click: The Ultimate Guide to Online Dating (releasing in February by Simon & Schuster) tells Mashable.
"In today’s apped-up, textaholic society, exploration means downloading apps, not just checking out a new You Tube video." Enter spur-of-the-moment dating.
As much as mobile dating apps are about the now, it's also important to note that if the notifications and constant messaging get overwhelming, it's okay to take a break.
"Don’t forget that most location-based apps have an off button," Davis says.Mobile app users aren't expected to wait and get to know the person before scheduling a meetup."The initial intention to meet focuses on fun, but that doesn’t mean that things can’t turn serious later as your relationship develops," Davis says.Eventually, Zhao’s algorithm will notice that while a client says he likes tall women, he keeps contacting short women, and will change its recommendations to him accordingly.“In our model, users with similar taste and (un)attractiveness will have higher similarity scores than those who only share common taste or attractiveness,” Zhao says.It’s similar to the model Netflix uses to recommend movies users might like by tracking their viewing history.