Ever wonder what social media sites do with the information they collect and store about their users? Well now, an upstart company called Wings is using that data to recommend potential love interests. The process works much like the way Netflix recommends movies based on viewing history and user ratings. Wings analyzes clues left on social media sites to help the user find suitable dating prospects. With traditional matchmaking sights, you tell the service all about yourself. With this new service, it tells you about yourself.
An article in Technology Review explains how the technology works:
[The] data is fed into the service’s recommendation engine. That system combines Bayesian modeling, a type of mathematical analysis that lets computers draw inferences from huge data sets, and machine learning, where the more data and feedback the algorithm is fed, the “smarter” it gets. The idea is that the computer’s analysis of your behavior provides a richer analysis than what you’d say about yourself.
For example:
The dating-recommendation site Wings analyzes your social media habits and populates your profile with information about who you are, what kind of music you like, and whether your tastes are “trendy” or “underground.”
Users of online matchmaking sites sometimes get in their own way by being less than completely honest or complete. Social media usage can reveal things about ourselves that are important to choosing a potential match that might not occur to us or that may have been disregarded or relegated to extant memories.
Sunil Nagaraj, chief executive and cofounder of Triangulate, Wing’s parent company, brings home that point:
“We serve as our own blind spot in that it’s difficult to accurately answer questions about oneself without biasing toward recent experience, current mood, etc.”
One example of an important matching factor that may not be immediately apparent or intuitive is the density of one’s social network. It turns out that if your friends are often friends with each other, you’re more likely to be compatible with someone who also has a tight network of friends.