In Analyzing Love: Data Mining on Match.com, I blogged about how the company mines the data created by user interactions on its site. This time, the company teamed with biological anthropologist Dr. Helen Fisher, evolutionary biologist Dr. Justin R. Garcia, and sex and relationship expert Dr. Laura Bermanto to delve into preferences and motivations.
Some may remain skeptical about using data to predict the success of personal relationships. But the data reveals some clues about why singles may choose to enter relationships and how satisfied they are within those relationships based on a variety of factors.
For example, the data suggests men are more likely to fall in love at first sight, more likely to make a commitment either without being in love or without feeling sexually attracted to a partner, and more likely to make public displays of affection.
In addition, it shows that political affiliation may determine the qualities singles seek in partners and how satisfied they are once in a relationship. Liberal Democrats are more likely to seek someone with a sense of humor and similar lifestyle while conservative Republicans are more likely to be searching for someone from the same background and political party and one interested in marriage, the data shows. (As an interesting side note, conservative Republicans apparently outdistance all other groups in being most satisfied with their sex life while married.)
We might ask whether we could use this data, and much more like it, to predict future relationships between singles. Would it be possible to determine happiness and stability of relationships in advance? (Match.com gives no clear indications in the release of what it intends to do with the survey results.) Some additional questions arise.
Can we trust the accuracy of the information users share? Obviously, some will raise doubt over data collected directly from, say, Match.com's user profiles, since users may enhance that information to impress others. Survey results seem more reliable since Match.com keeps respondent names confidential.
Also, did those giving the survey ask the right questions? We can wonder how they defined political affiliations like liberal and conservative, for example, or the term "commitment." We also can ask how Match.com defined "relationship" and the characteristics it considered as marking a successful relationship.
What do you think? Can data help predict love? We'll wait to hear from you on the comment boards.