Reciprocal recommender system online dating
Using data collected from Baihe, one of the largest dating websites in China, researchers from Binghamton University, University of Massachusetts Lowell and Northeastern University developed a reciprocal recommendation system that better matches users who are mutually interested in and likely to communicate with each other.Binghamton University Ph D candidate Shuangfei Zhai is co-author of the paper, along with Benyuan Liu, Yizhou Sun, Cindy Chen and lead researcher Peng Xia.A similar 2012 study suggested that men are more concerned with photos, and perhaps, looks, in online dating.The researchers used a Tobii X1 Light Eye Tracker, which recorded the eye movements of users who were reading online dating profiles from and e In particular, males tend to be focused on their own interests and be oblivious toward their attractiveness to potential dates, while females are more conscious of their own attractiveness.When it comes to messaging users on dating websites, men tend to be more aggressive and contact users they are interested in, whereas women tend to be more conscious of their own attractiveness to other users, according to new research.
When looking for potential matches, the research shows that women take their own attractiveness into consideration, whereas men are more oblivious to this.
Zhai and her colleagues from Binghamton, as well as the University of Massachusetts Lowell and Northeastern University worked to develop a reciprocal recommendation system that resembled Baihe, one of the largest dating sites in China, in order to match people who are mutually interested and likely to communicate with each other.
This is different from traditional user-item recommendations where the goal is to match items, such as books and videos, with a user's interests.
Here, the researchers introduced similarity measures: “interest similarity” gauged whether two users send messages to the same users, while “attractiveness similarity” measured whether they received messages from the same users.
In the end, the researchers analyzed a reciprocal score that measured the compatibility between a user and each potential dating candidate to find the “perfect match.”The findings revealed "interesting behavioral difference(s) between male and female users when it comes to looking for potential dates,” wrote the researchers.