Predicting Romantic Interest during Early Relationship Development: A Preregistered Investigation using Machine Learning

Abstract

There are massive literatures on initial romantic attraction and established, “official” relationships. But there is a gap in our knowledge about early relationship development: the interstitial stretch of time in which people experience rising and falling romantic interest for partners who have the potential to—but often do not—become sexual or dating partners. In the current study, 208 single participants reported on 1,065 potential romantic partners across 7,179 data points over seven months. In stage 1 of the analyses, we used machine learning (specifically, Random Forests) to extract estimates of the extent to which different classes of predictors (e.g., individual differences vs. target-specific constructs) accounted for participants’ romantic interest in these potential partners (12% vs. 36%, respectively). Also, the machine learning analyses offered little support for perceiver × target moderation accounts of compatibility: the meta-theoretical perspective that some types of perceivers are likely to experience greater romantic interest for some types of targets. In stage 2, we used traditional multilevel-modeling approaches to depict growth-curve analyses for each predictor retained by the machine learning models; robust (positive) main effects emerged for many variables, including sociosexuality, gender, the potential partner’s positive attributes (e.g., attractive, exciting), attachment features (e.g., proximity seeking, separation distress), and perceived interest. We also directly tested (and found no support for) ideal partner preference-matching effects on romantic interest, which is one popular perceiver × target moderation account of compatibility. We close by discussing the need for new models and perspectives to explain how people assess romantic compatibility.

Initial impressions of compatibility and mate value predict later dating and romantic interest

“… 39 ), first impressions are also bound to change, as reflected by the overall small-to-moderate effect sizes in the current study. For example, research suggests that relationship effects wax and partner effects wane as people get to know each other ( 14 , 40 ). Future studies should incorporate how impressions change during relationship initiation.…”

“…Although these datasets have been in previous publications (e.g., refs. 25 , 29 , 30 , 40 , 43 ), no prior articles used initial desire (measured at speed dating) to prospectively predict relationship initiation (measured during the follow-up period), as was done in the current study.…”

Mate evaluation theory.

“…The established relationships machine-learning study (Joel et al, 2020) reported that the addition of individual differences to the perceiver’s perception of their relationship with the target accounted for less than 1% of the variance in satisfaction and commitment. Another study (Eastwick et al, in press) examined an early relationship development context in which perceivers were reporting on targets in whom they were romantically interested (i.e., potential romantic partners, crushes). In this study, Perceiver individual difference × Perception of target interactions accounted for 3% of the variance.…”

“…These two approaches encompass most empirical tests of moderation by individual differences (i.e., Perceiver × Target interactions); such hypotheses are ubiquitous in the literature and are commonly derived from a wide variety of close relationships (e.g., Girme et al, 2021; Luerssen et al, 2017; Wang et al, 2021) and evolutionary psychological (e.g., Brown & Sacco, 2017; Lamela et al, 2020; Meltzer et al, 2014) perspectives (cf. Eastwick et al, in press).…”

Inferring one's own attitude toward an unknown attribute: The moderating role of complexity in juice tasting

“…Human mating researchers have also measured functional preferences, albeit less commonly than summarized preferences. For instance, in one set of studies (Brumbaugh & Wood, 2013; Wood & Brumbaugh, 2009), researchers computed participants' functional preferences as the within‐person correlation of (a) the level of an attribute depicted in each of a set of faces (e.g., “confident”) with (b) the participant's attraction ratings to each face (see also DeBruine et al, 2006; Eastwick et al, in press).…”