Machine learning uncovers the most robust self-report predictors of relationship quality across 43 longitudinal couples studies

S. Joel and others
Proceedings of the National Academy of Sciences 
Aug 2020, 117 (32) 19061-19071
DOI: 10.1073/pnas.1917036117

Abstract

Given the powerful implications of relationship quality for health and well-being, a central mission of relationship science is explaining why some romantic relationships thrive more than others. This large-scale project used machine learning (i.e., Random Forests) to 1) quantify the extent to which relationship quality is predictable and 2) identify which constructs reliably predict relationship quality. Across 43 dyadic longitudinal datasets from 29 laboratories, the top relationship-specific predictors of relationship quality were perceived-partner commitment, appreciation, sexual satisfaction, perceived-partner satisfaction, and conflict. The top individual-difference predictors were life satisfaction, negative affect, depression, attachment avoidance, and attachment anxiety. Overall, relationship-specific variables predicted up to 45% of variance at baseline, and up to 18% of variance at the end of each study. Individual differences also performed well (21% and 12%, respectively). Actor-reported variables (i.e., own relationship-specific and individual-difference variables) predicted two to four times more variance than partner-reported variables (i.e., the partner’s ratings on those variables). Importantly, individual differences and partner reports had no predictive effects beyond actor-reported relationship-specific variables alone. These findings imply that the sum of all individual differences and partner experiences exert their influence on relationship quality via a person’s own relationship-specific experiences, and effects due to moderation by individual differences and moderation by partner-reports may be quite small. Finally, relationship-quality change (i.e., increases or decreases in relationship quality over the course of a study) was largely unpredictable from any combination of self-report variables. This collective effort should guide future models of relationships.

Significance

What predicts how happy people are with their romantic relationships? Relationship science—an interdisciplinary field spanning psychology, sociology, economics, family studies, and communication—has identified hundreds of variables that purportedly shape romantic relationship quality. The current project used machine learning to directly quantify and compare the predictive power of many such variables among 11,196 romantic couples. People’s own judgments about the relationship itself—such as how satisfied and committed they perceived their partners to be, and how appreciative they felt toward their partners—explained approximately 45% of their current satisfaction. The partner’s judgments did not add information, nor did either person’s personalities or traits. Furthermore, none of these variables could predict whose relationship quality would increase versus decrease over time.

Sex robots are coming. We might even fall in love with them.

Sean Illing
www.vox.com
Originally published May 11, 2018

Here is an excerpt:

Sean Illing: Your essay poses an interesting question: Is mutual love with a robot possible? What’s the answer?

Lily Eva Frank:

Our essay tried to explore some of the core elements of romantic love that people find desirable, like the idea of being a perfect match for someone or the idea that we should treasure the little traits that make someone unique, even those annoying flaws or imperfections.

The key thing is that we love someone because there’s something about being with them that matters, something particular to them that no one else has. And we make a commitment to that person that holds even when they change, like aging, for example.

Could a robot do all these things? Our answer is, in theory, yes. But only a very advanced form of artificial intelligence could manage it because it would have to do more than just perform as if it were a person doing the loving. The robot would have to have feelings and internal experiences. You might even say that it would have to be self-aware.

But that would leave open the possibility that the sex bot might not want to have sex with you, which sort of defeats the purpose of developing these technologies in the first place.

(cut)

I think people are weird enough that it is probably possible for them to fall in love with a cat or a dog or a machine that doesn’t reciprocate the feelings. A few outspoken proponents of sex dolls and robots claim they love them. Check out the testimonials page on the websites of sex doll manufactures; they say things like, “Three years later, I love her as much as the first day I met her.” I don’t want to dismiss these people’s reports.

The information is here.

Is Pulling the Lever Sexy? Deontology as a Downstream Cue to Long-Term Mate Quality

Mitch Brown and Donald Sacco
Journal of Social and Personal Relationships
November 2017

Abstract

Deontological and utilitarian moral decisions have unique communicative functions within the context of group living. Deontology more strongly communicates prosocial intentions, fostering greater perceptions of trust and desirability in general affiliative contexts. This general trustworthiness may extend to perceptions of fidelity in romantic relationships, leading to perceptions of deontological persons as better long-term mates, relative to utilitarians. In two studies, participants indicated desirability of both deontologists and utilitarians in long- and short-term mating contexts. In Study 1 (n = 102), women perceived a deontological man as more interested in long-term bonds, more desirable for long-term mating, and less prone to infidelity, relative to a utilitarian man. However, utilitarian men were undesirable as short-term mates. Study 2 (n = 112) had both men and women rate opposite sex targets’ desirability after learning of their moral decisions in a trolley problem. We replicated women’s preference for deontological men as long-term mates. Interestingly, both men and women reporting personal deontological motives were particularly sensitive to deontology communicating long-term desirability and fidelity, which could be a product of the general affiliative signal from deontology. Thus, one’s moral basis for decision-making, particularly deontologically-motivated moral decisions, may communicate traits valuable in long-term mating contexts.

The research is here.