Predicting Romantic Interest during Early Relationship Development: A Preregistered Investigation using Machine Learning
Bibliographic record
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.015 | 0.048 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".