Computers can predict little about attraction

Can that quiz on Facebook really tell you who your future soulmate is?

While most won’t believe it, a lot of people do put faith in dating websites that claim they can predict attraction between two people using a concoction of characteristics and preferences.

Are these people being deceived?

According to recent findings, it is indeed possible for computer software to predict how desirable certain types of people are to the user.

However, this does not mean the software will find a person their perfect soulmate.

Contrary to the promises made by online dating advertisements, researchers found that computers have a hard time predicting the unique attraction between two specific people.

A recent study led by Samantha Joel, psychology professor at the University of Utah, investigated the phenomena using speed-dating data.

This study, titled “Is Romantic Desire Predictable? Machine Learning Applied to Initial Romantic Action,” was published in the journal Psychological Science.

In the study, the team of researchers used data from two groups of individuals who answered surveys with hundreds of questions about their characteristics, hobbies and preferences that they would list on their dating profile.

Immediately following the questionnaire, the subjects met each other one on one in a series of four-minute dates. Afterward each participant rated their interaction with the person they met.

They were instructed to note their level of interest as well as sexual attraction to each person after each round of dates.

To analyze and interpret the result of these speed-dating sessions, Joel and her team of researchers used a new machine learning algorithm to determine whether it is possible to predict unique romantic attraction before two people meet, solely by looking at their survey answers.

And what was the verdict to their research? No, online. At least with the current research techniques and instrumentation available, researchers are unable to predict whether a prospective couple will find true love using online dating services.

The algorithm could predict the general tendency or trend for one type of person to like or be liked by another but not whether two specific individuals in the group are going to be a good match.

The desire for a soulmate creates a demand for the online dating market. Joel’s study shows that in the case of dating, there is not a shortcut to finding the perfect partner.

“Attraction for a particular person may be difficult or impossible to predict before two people have actually met,” Joel said according to ScienceDaily. “Our data suggests that, at least with the tools we currently have available, there isn’t an easy fix for finding love.”

Online dating websites and platforms can often do a service for users by determining potential romantic partners and perhaps narrowing the choices down to the more relevant candidates.

However, in the end, dating still requires meeting people face to face.

Paul W. Eastwick, one of the co-authors of the study, admitted to ScienceDaily that romantic attraction extends beyond chemical reactions and that there are many more factors to consider when studying love.

“Romantic desire [is] more like an earthquake, involving a dynamic and chaos-like process, than a chemical reaction involving the right combination of traits and preferences,”Eastwick said.