Is romantic desire predictable? Machine learning applied to initial romantic attraction

Joel, Samantha (2018). Is romantic desire predictable? Machine learning applied to initial romantic attraction. [Data Collection]. Colchester, Essex: UK Data Archive. 10.5255/UKDA-SN-852716

Data description (abstract)

We used machine learning to test how well such measures predict people’s overall tendencies to romantically desire others (actor variance) and to be desired by others (partner variance), as well as desire for specific partners above and beyond actor and partner variance (relationship variance). Close relationships theoretical perspectives and matchmaking companies suggest that initial attraction is, to some extent, a product of two people’s self-reported traits and preferences. In two speed-dating studies, romantically unattached individuals completed over one hundred traits and preferences identified by past research as relevant to mate selection. Participants then met one another in a series of four-minute speed-dates. Random forests models predicted 4-18% of actor variance and 7-27% of partner variance, but, crucially, they were unable to predict relationship variance using any combination of traits and preferences reported beforehand. These results suggest that compatibility elements of human mating are challenging to predict before two people meet.

Downloads

Altmetric