Is Romantic Desire Predictable? Machine Learning Applied to Initial Romantic Attraction

Simultaneous clustering and variable selection: A novel algorithm and model selection procedure

The growing availability of high-dimensional data sets offers behavioral scientists an unprecedented opportunity to integrate the information hidden in the novel types of data (e.g., genetic data, social media data, and GPS tracks, etc.,) and thereby obtain a more detailed and comprehensive view towards their research questions. In the context of clustering, analyzing the large volume of variables could potentially result in an accurate estimation or a novel discovery of underlying subgroups. However, a unique challenge is that the high-dimensional data sets likely involve a significant amount of irrelevant variables. These irrelevant variables do not contribute to the separation of clusters and they may mask cluster partitions. The current paper addresses this challenge by introducing a new clustering algorithm, called Cardinality K-means or CKM, and by proposing a novel model selection strategy. CKM is able to perform simultaneous clustering and variable selection with high stability. In two simulation studies and an empirical demonstration with genetic data, CKM consistently outperformed competing methods in terms of recovering cluster partitions and identifying signaling variables. Meanwhile, our novel model selection strategy determines the number of clusters based on a subset of variables that are most likely to be signaling variables. Through a simulation study, this strategy was found to result in a more accurate estimation of the number of clusters compared to the conventional strategy that utilizes the full set of variables. Our proposed CKM algorithm, together with the novel model selection strategy, has been implemented in a freely accessible R package.

Stability and Change of Individual Differences in Ideal Partner Preferences Over 13 Years

Ideal partner preferences for traits in a partner are said to be stable cognitive constructs. However, longitudinal studies investigating the same participants' ideals repeatedly have so far been limited to relatively short retest intervals of a maximum of 3 years. Here, we investigate the stability and change of ideals across 13 years and participants' insight into how ideals have changed. A total of 204 participants (M = 46.2 years, SD = 7.4, 104 women) reported their ideals at two time points. We found a mean rank-order stability of r = .42 and an overall profile stability of r = .73 (distinctive r = .53). Some ideals changed over time, for example, increased for status-resources in relation to age and parenthood. We found some but varying insight into how ideals had changed (mean r = .20). Results support the idea of ideals being stable cognitive constructs but suggest some variability related to the demands of different life stages.

Penalized for Challenging Traditional Gender Roles: Why Heterosexual Relationships in Which Women Wear the Pants May Be More Precarious

There is growing evidence that heterosexual relationships in which traditional gender roles are reversed because women have attained higher societal status than their male partner are more precarious. We argue that this is the case because both partners in role-reversed relationships are evaluated more negatively than partners in more egalitarian or traditional gender role relationships. In two experimental studies conducted in the United States (N = 223) and the Netherlands (N = 269), we found that when encountering role-reversed relationships, participants perceive the woman as the more dominant and agentic one and the man as the weaker one in the relationship. They also perceive women in role-reversed relationships as less likeable, have less respect for men in role-reversed relationships, and expect that such relationships are less satisfying. In addition, in a third partner study (N = 94 heterosexual couples), we found that both male and female partners in role-reversed relationships considered the man to be the weaker one and the woman to be the more dominant one. Moreover, perceiving the man as the weaker one predicted lower relationship satisfaction in role-reversed couples. Overall, this research indicates that gender stereotypes about heterosexual relationships should be considered in efforts to achieve gender equity.

A Machine Learning Approach to Predicting Perceived Partner Support From Relational and Individual Variables

Perceiving one’s partner as supportive is considered essential for relationships, but we know little about which factors are central to predicting perceived partner support. Traditional statistical techniques are ill-equipped to compare a large number of potential predictor variables and cannot answer this question. This research used machine learning analysis (random forest with Shapley values) to identify the most salient self-report predictors of perceived partner support cross-sectionally and 6 months later. We analyzed data from five dyadic data sets ( N = 550 couples) enabling us to have greater confidence in the findings and ensure generalizability. Our novel results advance the literature by showing that relationship variables and attachment avoidance are central to perceived partner support, whereas partner similarity, other individual differences, individual well-being, and demographics explain little variance in perceiving partners as supportive. The findings are crucial in constraining and further developing our theories on perceived partner support.

Neural Processing of Facial Attractiveness and Romantic Love: An Overview and Suggestions for Future Empirical Studies

Romantic love is universally observed in human communities, and the manner in which a person chooses a long-term romantic partner has been a central question in studies on close relationships. Numerous empirical psychological studies have demonstrated that facial attractiveness greatly impacts initial romantic attraction. This close link was further investigated by neuroimaging studies showing that both viewing attractive faces and having romantic thoughts recruit the reward system. However, it remains unclear how our brains integrate perceived facial attractiveness into initial romantic attraction. In addition, it remains unclear how our brains shape a persistent attraction to a particular person through interactions; this persistent attraction is hypothesized to contribute to a long-term relationship. After reviewing related studies, I introduce methodologies that could help address these questions.

The Psychology of Personalization in Digital Environments: From Motivation to Well-Being – A Theoretical Integration

The personalization of digital environments is becoming ubiquitous due to the rise of AI-based algorithms and recommender systems. Arguably, this technological development has far-reaching consequences for individuals and societies alike. In this article, we propose a psychological model of the effects of personalization in digital environments, which connects personalization with motivational tendencies, psychological needs, and well-being. Based on the model, we review studies from three areas of application—news feeds and websites, music streaming, and online dating—to explain both the positive and the negative effects of personalization on individuals. We conclude that personalization can lead to desirable outcomes such as reducing choice overload. However, personalized digital environments without transparency and without the option for users to play an active role in the personalization process potentially pose a danger to human well-being. Design recommendations as well as avenues for future research that follow from these conclusions are being discussed.

Predicting romantic interest during early relationship development: A preregistered investigation using machine learning

There are massive literatures on initial attraction and established relationships. But few studies capture early relationship development: the interstitial period in which people experience rising and falling romantic interest for partners who could—but often do not—become sexual or dating partners. In this study, 208 single participants reported on 1,065 potential romantic partners across 7,179 data points over 7 months. In stage 1, we used random forests (a type of machine learning) to estimate how well different classes of variables (e.g., individual differences vs. target-specific constructs) predicted participants’ romantic interest in these potential partners. We also tested (and found only modest support for) the perceiver × target moderation account of compatibility: the meta-theoretical perspective that some types of perceivers experience greater romantic interest for some types of targets. In stage 2, we used multilevel modeling to depict predictors retained by the random-forests models; robust (positive) main effects emerged for many variables, including sociosexuality, sex drive, perceptions of the partner’s positive attributes (e.g., attractive and exciting), attachment features (e.g., proximity seeking), and perceived interest. Finally, we found no support for ideal partner preference-matching effects on romantic interest. The discussion highlights the need for new models to explain the origin of romantic compatibility.

Is Mate Preference Recognizable Based on Electroencephalogram Signals? Machine Learning Applied to Initial Romantic Attraction

Initial romantic attraction (IRA) refers to a series of positive reactions toward potential ideal partners based on individual preferences; its evolutionary value lies in facilitating mate selection. Although the EEG activities associated with IRA have been preliminarily understood; however, it remains unclear whether IRA can be recognized based on EEG activity. To clarify this, we simulated a dating platform similar to Tinder. Participants were asked to imagine that they were using the simulated dating platform to choose the ideal potential partner. Their brain electrical signals were recorded as they viewed photos of each potential partner and simultaneously assessed their initial romantic attraction in that potential partner through self-reported scale responses. Thereafter, the preprocessed EEG signals were decomposed into power-related features of different frequency bands using a wavelet transform approach. In addition to the power spectral features, feature extraction also accounted for the physiological parameters related to hemispheric asymmetries. Classification was performed by employing a random forest classifier, and the signals were divided into two categories: IRA engendered and IRA un-engendered. Based on the results of the 10-fold cross-validation, the best classification accuracy 85.2% (SD = 0.02) was achieved using feature vectors, mainly including the asymmetry features in alpha (8–13 Hz), beta (13–30 Hz), and theta (4–8 Hz) rhythms. The results of this study provide early evidence for EEG-based mate preference recognition and pave the way for the development of EEG-based romantic-matching systems.

Is Infidelity Predictable? Using Explainable Machine Learning to Identify the Most Important Predictors of Infidelity

Infidelity can be a disruptive event in a romantic relationship with a devastating impact on both partners' well-being. Thus, there are benefits to identifying factors that can explain or predict infidelity, but prior research has not utilized methods that would provide the relative importance of each predictor. We used a machine learning algorithm, random forest (a type of interpretable highly non-linear decision tree), to predict in-person and online infidelity across two studies (one individual and one dyadic, N = 1,295). We also used a game theoretic explanation technique, Shapley values, which allowed us to estimate the effect size of each predictor variable on infidelity. The present study showed that infidelity was somewhat predictable overall and interpersonal factors such as relationship satisfaction, love, desire, and relationship length were the most predictive of online and in person infidelity. The results suggest that addressing relationship difficulties early in the relationship may help prevent infidelity.

We Don't Choose Whom We Love: Predictors for Romantic Attraction to Villains

INTRODUCTION

Why are women (not) romantically attracted to dark personalities or villains, which might be a risk factor for intimate partner violence (IPV) victimization? In the current study, it is opted to investigate how adult attachment, maladaptive personality traits, and acceptance of couple violence in women predict romantic attraction to heroic/villainous characters using structural equation modeling (SEM).

METHOD

First, a pilot study was conducted in 122 heterosexual women (aged 16-25) to select male TV characters. This resulted in the selection of six villains and 10 heroes for the main study, in which 194 other heterosexual women (aged 16-25) were asked to rate the pictures of TV characters through an online questionnaire. This was combined with self-report measures of maladaptive personality traits, acceptance of couple violence, and adult attachment. These variables were entered into a SEM model to assess model fit.

RESULTS

Overall, women rated heroes higher on physical appearance (pilot study) and romantic attraction (main study) compared to villains. We found different direct effects of avoidant (negative) and anxious (positive) attachment styles on romantic attraction to heroes. Moreover, maladaptive personality traits fully mediated the positive effect of avoidant attachment style on romantic attraction to villains.

DISCUSSION

Despite the limitations of the study design (e.g., low N, low notoriety of the TV characters), this study emphasizes that women are generally more romantically attracted to heroes (vs. villains). Besides, there are different predictors of romantic attraction to heroes and villains, which requires further investigation, especially in the context of IPV.

The Brain Understands Social Relationships: The Emerging Field of Functional-Connectome-Based Interpersonal Research

Human functional brain imaging research over the last 2 decades has shown that data from resting-state brain activity can help predict various psychological and pathological variables and brain function during tasks. However, most variables have been attributed to the individual brain. Recently, several studies have aimed to understand interpersonal relationships based on inter-individual similarity or dissimilarity of functional connectome. In this commentary, we introduce the studies that have opened up a new era of interpersonal research using human brain imaging.

Pupil Size Predicts Partner Choices in Online Dating

People's choices for specific romantic partners can have far reaching consequences, but very little is known about the process of partner selection. In the current study, we tested whether a measure of physiological arousal, pupillometry (i.e., changes in pupil size), can predict partner choices in an online dating setting. A total of 239 heterosexual participants took part in an online dating task in which they accepted or rejected hypothetical potential partners, while pupil size response was registered using an eye tracker. In line with our main hypothesis, the results indicated a positive association between pupil size and partner acceptance. This association was not found to depend on relationship status, relationship quality, gender, or sociosexual orientation. These findings show that the body (i.e., the pupils) provides an automatic cue of whether a potential partner will be selected as a mate, or rejected.

We're Not That Choosy: Emerging Evidence of a Progression Bias in Romantic Relationships

Dating is widely thought of as a test phase for romantic relationships, during which new romantic partners carefully evaluate each other for long-term fit. However, this cultural narrative assumes that people are well equipped to reject poorly suited partners. In this article, we argue that humans are biased toward pro-relationship decisions-decisions that favor the initiation, advancement, and maintenance of romantic relationships. We first review evidence for a progression bias in the context of relationship initiation, investment, and breakup decisions. We next consider possible theoretical underpinnings-both evolutionary and cultural-that may explain why getting into a relationship is often easier than getting out of one, and why being in a less desirable relationship is often preferred over being in no relationship at all. We discuss potential boundary conditions that the phenomenon may have, as well as its implications for existing theoretical models of mate selection and relationship development.

Brain Knows Who Is on the Same Wavelength: Resting-State Connectivity Can Predict Compatibility of a Female-Male Relationship

Prediction of the initial compatibility of heterosexual individuals based on self-reported traits and preferences has not been successful, even with significantly developed information technology. To overcome the limitations of self-reported measures and predict compatibility, we used functional connectivity profiles from resting-state functional magnetic resonance imaging (fMRI) data that carry rich individual-specific information sufficient to predict psychological constructs and activation patterns during social cognitive tasks. Several days after collecting data from resting-state fMRIs, participants undertook a speed-dating experiment in which they had a 3-min speed date with every other opposite-sex participant. Our machine learning algorithm successfully predicted whether pairs in the experiment were compatible or not using (dis)similarity of functional connectivity profiles obtained before the experiment. The similarity and dissimilarity of functional connectivity between individuals and these multivariate relationships contributed to the prediction, hence suggesting the importance of complementarity (observed as dissimilarity) as well as the similarity between an individual and a potential partner during the initial attraction phase. The result indicates that the salience network, limbic areas, and cerebellum are especially important for the feeling of compatibility. This research emphasizes the utility of neural information to predict complex phenomena in a social environment that behavioral measures alone cannot predict.

Racial preferences in sexual attraction among White heterosexual and gay men: Evidence from sexual arousal patterns and negative racial attitudes

Racial preferences in sexual attraction are highly visible and controversial. They may also negatively impact those who are excluded. It is unclear whether these preferences are merely self-attributed or extend to patterns of experienced sexual arousal. Furthermore, some argue that racial preferences in sexual attraction reflect idiosyncratic personal preferences, while others argue that they are more systematically motivated and reflect broader negative attitudes toward particular races. In two studies, we examined these issues by measuring the sexual arousal patterns and negative racial attitudes of 78 White men in relation to their racial preferences in sexual attraction to White versus Black people. For both White heterosexual men (n = 40; Study 1) and White gay men (n = 38; Study 2), greater racial preferences in sexual attraction to White versus Black people of their preferred gender were associated with more subjective and genital arousal by erotic stimuli featuring White versus Black people of their preferred gender, and with more explicit and implicit negative attitudes toward Black people. Findings suggest that racial preferences in sexual attraction are reflected in patterns of sexual arousal, and they might also be systematically motivated by negative attitudes toward particular races.

Body sway predicts romantic interest in speed dating

Social bonding is fundamental to human society, and romantic interest involves an important type of bonding. Speed dating research paradigms offer both high external validity and experimental control for studying romantic interest in real-world settings. While previous studies focused on the effect of social and personality factors on romantic interest, the role of non-verbal interaction has been little studied in initial romantic interest, despite being commonly viewed as a crucial factor. The present study investigated whether romantic interest can be predicted by non-verbal dyadic interactive body sway, and enhanced by movement-promoting (‘groovy’) background music. Participants’ body sway trajectories were recorded during speed dating. Directional (predictive) body sway coupling, but not body sway similarity, predicted interest in a long-term relationship above and beyond rated physical attractiveness. In addition, presence of groovy background music promoted interest in meeting a dating partner again. Overall, we demonstrate that romantic interest is reflected by non-verbal body sway in dyads in a real-world dating setting. This novel approach could potentially be applied to investigate non-verbal aspects of social bonding in other dynamic interpersonal interactions such as between infants and parents and in non-verbal populations including those with communication disorders.

Uncovering the Most Important Factors for Predicting Sexual Desire Using Explainable Machine Learning

BACKGROUND

Low sexual desire is the most common sexual problem reported with 34% of women and 15% of men reporting lack of desire for at least 3 months in a 12-month period. Sexual desire has previously been associated with both relationship and individual well-being highlighting the importance of understanding factors that contribute to sexual desire as improving sexual desire difficulties can help improve an individual's overall quality of life.

AIM

The purpose of the present study was to identify the most salient individual (eg, attachment style, attitudes toward sexuality, gender) and relational (eg, relationship satisfaction, sexual satisfaction, romantic love) predictors of dyadic and solitary sexual desire from a large number of predictor variables.

METHODS

Previous research has relied primarily on traditional statistical models which are limited in their ability to estimate a large number of predictors, non-linear associations, and complex interactions. We used a machine learning algorithm, random forest (a type of highly non-linear decision tree), to circumvent these issues to predict dyadic and solitary sexual desire from a large number of predictors across 2 online samples (N = 1,846; includes 754 individuals forming 377 couples). We also used a Shapley value technique to estimate the size and direction of the effect of each predictor variable on the model outcome.

OUTCOMES

The outcomes included total, dyadic, and solitary sexual desire measured using the Sexual Desire Inventory.

RESULTS

The models predicted around 40% of variance in dyadic and solitary desire with women's desire being more predictable than men's overall. Several variables consistently predicted dyadic sexual desire such as sexual satisfaction and romantic love, and solitary desire such as masturbation and attitudes toward sexuality. These predictors were similar for both men and women and gender was not an important predictor of sexual desire.

CLINICAL TRANSLATION

The results highlight the importance of addressing overall relationship satisfaction when sexual desire difficulties are presented in couples therapy. It is also important to understand clients' attitudes toward sexuality.

STRENGTHS & LIMITATIONS

The study improves on existing methodologies in the field and compares a large number of predictors of sexual desire. However, the data were cross-sectional and there may have been variables that are important for desire but were not present in the datasets.

CONCLUSION

Higher sexual satisfaction and feelings of romantic love toward one's partner are important predictors of dyadic sexual desire whereas regular masturbation and more permissive attitudes toward sexuality predicted solitary sexual desire. Vowels LM, Vowels MJ, Mark KP. Uncovering the Most Important Factors for Predicting Sexual Desire Using Explainable Machine Learning. J Sex Med 2021;18:1198-1216.

When Forecasting Mutually Supportive Matches Will Be Practically Impossible

Forecasting which dyads will develop mutually supportive relationships is an important applied and basic research question. Applying psychometric theory to the design of forecasting studies shows that agreement between dyad members about their relationship (relational reciprocity) sets an upper limit for forecasting accuracy by determining the reliability of measurement. To test this, we estimated relational reciprocity in Study 1. Participants in seven samples (six student and one military; N = 504; N_dyads = 766) rated each other on support-related constructs in round-robin designs. Relational reciprocity was very low, undermining reliability. Formulas from psychometric theory predicted that forecasting supportive dyads would be practically impossible. To test this, we had participants in Study 2 complete a measure for matching dyads derived from recent theory. As predicted, supportive matches could not be forecast with acceptable precision. Theoretically, this falsifies some predictions of recent social-support theory. Practically, it remains unclear how to translate basic social-support research into effective interventions.

Efficacy of the web-based PaarBalance program on relationship satisfaction, depression and anxiety - A randomized controlled trial

OBJECTIVE

Although relationship distress is strongly associated with mental health problems, poorer social functioning and lower quality of life, only a minority of distressed couples engage in effective couples therapy. Common barriers are the financial burden, fear of being stigmatized, long waitlists and logistical concerns, such as the difficulty in scheduling appointments. Therefore, more accessible help for relationship distress is needed, such as internet-based interventions.

METHOD

This study evaluates the efficacy of the German web-based PaarBalance program, an 18-sessions online program for couples and individuals in an intimate relationship. Participants with relationship distress recruited via the internet had access to the unguided self-help program for twelve weeks. A total of 117 individuals (N = 60 participated as couples, N = 57 participated without a partner) were randomly assigned to begin the intervention immediately or to a 12-week waitlist control group. The primary outcome was relationship satisfaction. Secondary outcomes included symptoms of depression and anxiety.

RESULTS

The intervention group showed significant improvement in relationship satisfaction (Cohen's d =0.77) compared with the waitlist control group. Small to medium effect sizes in favor of the intervention group, but no statistically significant differences were found regarding depression (d = 0.43) and anxiety (d = 0.45).

CONCLUSION

PaarBalance seems to be an effective self-guided intervention to improve relationship satisfaction in people with relationship problems.

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

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.

Blind at First Sight: The Role of Distinctively Accurate and Positive First Impressions in Romantic Interest

Viewing other people with distinctive accuracy-the degree to which personality impressions correspond with targets' unique characteristics-often predicts positive interpersonal experiences, including liking and relationship satisfaction. Does this hold in the context of first dates, or might distinctive accuracy have negative links with romantic interest in such evaluative settings? We examined this question using two speed-dating samples (Sample 1: N = 172, N = 2,407 dyads; Sample 2: N = 397, N = 1,849 dyads). Not surprisingly, positive impressions of potential dating partners were strongly associated with greater romantic interest. In contrast, distinctively accurate impressions were associated with significantly less romantic interest. This association was even stronger for potential partners whose personalities were less romantically appealing, specifically, those lower in extraversion. In sum, on a first date, distinctive accuracy tends to be paired with lower romantic interest. The potential implications of distinctive accuracy for romantic interest and of romantic interest for distinctive accuracy are discussed.

Hormones in speed-dating: The role of testosterone and cortisol in attraction

There is evidence that testosterone and cortisol levels are related to the attraction of a romantic partner; testosterone levels relate to a wide range of sexual behaviors and cortisol is a crucial component in the response to stress. To investigate this, we conducted a speed-dating study among heterosexual singles. We measured salivary testosterone and cortisol changes in men and women (n = 79) when they participated in a romantic condition (meeting opposite-sex others, i.e., potential romantic partners), as well as a control condition (meeting same-sex others, i.e., potential friends). Over the course of the romantic speed-dating event, results showed that women's but not men's testosterone levels increased and cortisol levels decreased for both men and women. These findings indicate that men's testosterone and cortisol levels were elevated in anticipation of the event, whereas for women, this appears to only be the case for cortisol. Concerning the relationship between attraction and hormonal change, four important findings can be distinguished. First, men were more popular when they arrived at the romantic speed-dating event with elevated cortisol levels. Second, in both men and women, a larger change in cortisol levels during romantic speed-dating was related to more selectivity. Third, testosterone alone was unrelated to any romantic speed-dating outcome (selectivity or popularity). However, fourth, women who arrived at the romantic speed-dating event with higher testosterone levels were more selective when their anticipatory cortisol response was low. Overall, our findings suggest that changes in the hormone cortisol may be stronger associated with the attraction of a romantic partner than testosterone.

Polar Similars: Using Massive Mobile Dating Data to Predict Synchronization and Similarity in Dating Preferences

Leveraging a massive dataset of over 421 million potential matches between single users on a leading mobile dating application, we were able to identify numerous characteristics of effective matching. Effective matching is defined as the exchange of contact information with the likely intent to meet in person. The characteristics of effective match include alignment of psychological traits (i.e., extroversion), physical traits (i.e., height), personal choices (i.e., desiring the same relationship type), and shared experiences. For nearly all characteristics, the more similar the individuals were, the higher the likelihood was of them finding each other desirable and opting to meet in person. The only exception was introversion, where introverts rarely had an effective match with other introverts. When investigating the preliminary stages of the choice process we looked at the consistency between the choice of men/women, the time it took users to make these binary choices, and the tendency of yes/no decisions. We used a biologically inspired choice model to estimate the decision process and could predict the selection and response time with nearly 60% accuracy. Given that people make their initial selection in no more than 11 s, and ultimately prefer a partner who shares numerous attributes with them, we suggest that users are less selective in their early preferences and gradually, during their conversation, converge onto clusters that share a high degree of similarity in characteristics.

Consistency between individuals' past and current romantic partners' own reports of their personalities

Do people have a "type" when it comes to their romantic partners' personalities? In the present research, we used data from a 9-y longitudinal study in Germany and examined the similarity between an individual's ex- and current partners using the partners' self-reported personality profiles. Based on the social accuracy model, our analyses distinguished similarity between partners that was attributable to similarity to an average person (normative similarity) and resemblance to the target participant himself/herself (self-partner similarity) to more precisely examine similarity from partner to partner (distinctive similarity). The results revealed a significant degree of distinctive partner similarity, suggesting that there may indeed be a unique type of person each individual ends up with. We also found that distinctive partner similarity was weaker for people high in extraversion or openness to experience, suggesting that these individuals may be less likely to be in a relationship with someone similar to their ex-partner (although the individual difference effects were not mirrored in an alternative analytic approach). These findings provide evidence for stability in distinctive partner personality and have important implications for predicting future partnering behaviors and actions in romantic relationships.

Machine learning in a data-limited regime: Augmenting experiments with synthetic data uncovers order in crumpled sheets

Machine learning has gained widespread attention as a powerful tool to identify structure in complex, high-dimensional data. However, these techniques are ostensibly inapplicable for experimental systems where data are scarce or expensive to obtain. Here, we introduce a strategy to resolve this impasse by augmenting the experimental dataset with synthetically generated data of a much simpler sister system. Specifically, we study spontaneously emerging local order in crease networks of crumpled thin sheets, a paradigmatic example of spatial complexity, and show that machine learning techniques can be effective even in a data-limited regime. This is achieved by augmenting the scarce experimental dataset with inexhaustible amounts of simulated data of rigid flat-folded sheets, which are simple to simulate and share common statistical properties. This considerably improves the predictive power in a test problem of pattern completion and demonstrates the usefulness of machine learning in bench-top experiments where data are good but scarce.

Machine learning meets partner matching: Predicting the future relationship quality based on personality traits

To what extent is it possible to use machine learning to predict the outcome of a relationship, based on the personality of both partners? In the present study, relationship satisfaction, conflicts, and separation (intents) of 192 partners four years after the completion of questionnaires concerning their personality traits was predicted. A 10x10-fold cross-validation was used to ensure that the results of the linear regression models are reproducible. The findings indicate that machine learning techniques can improve the prediction of relationship quality (37% of variance explained), and that the perceived relationship quality of a partner is mostly dependent on his or her own individual personality traits. Additionally, the influences of different sets of variables on predictions are shown: partner and similarity effects did not incrementally predict relationship quality beyond actor effects and general personality traits predicted relationship quality less strongly than relationship-related personality.

Speech Is Silver, Nonverbal Behavior Is Gold: How Implicit Partner Evaluations Affect Dyadic Interactions in Close Relationships

Growing evidence suggests that the seeds of relationship decay can be detected via implicit partner evaluations even when explicit evaluations fail to do so. However, little is known about the concrete daily relational processes that explain why these gut feelings are such important determinants of relationships’ long-term outcomes. The present integrative multimethod research yielded a novel finding: that participants with more positive implicit partner evaluations exhibited more constructive nonverbal (but not verbal) behavior toward their partner in a videotaped dyadic interaction. In turn, this behavior was associated with greater satisfaction with the conversation and with the relationship in the following 8-day diary portion of the study. These findings represent a significant step forward in understanding the crucial role of automatic processes in romantic relationships. Together, they provide novel evidence that relationship success appears to be highly dependent on how people spontaneously behave in their relationship, which may be ultimately rooted in their implicit partner evaluations.

Open Sharing of Data on Close Relationships and Other Sensitive Social Psychological Topics: Challenges, Tools, and Future Directions

This article reports on an adversarial (but friendly) collaboration examining the issues that lie at the intersection of confidentiality and open-data practices. We describe the process we followed to share our data for a speed-dating article we recently published in Psychological Science (Joel, Eastwick, & Finkel, 2017) and provide a summary of the issues we considered and addressed along the way. As we drafted the present article, the third author became unsure, in retrospect, about some of the procedures we had followed, especially if our approach were to be perceived as a model for open-data decisions in other, more typical cases involving nonindependent data. This article addresses these concerns, but also identifies areas of consensus. All three authors agree that there remains an unmet need for guidelines and other resources to help researchers address the challenges of sharing data that cover sensitive topics, particularly nonindependent data collected from pairs and groups (e.g., romantic couples, work teams, therapy groups). We conclude with a discussion of new tools that could be developed to help scholars who have collected such data to increase the transparency of their research while simultaneously protecting the confidentiality of the participants.

Intervening Earlier: An Upstream Approach to Improving Relationship Quality

Relationship quality has far-reaching consequences for health and well-being. To date, large-scale efforts to improve relationship quality have targeted established relationships. However, a novel approach would be to target relationships much earlier. Investment-based programs would intervene (on a voluntary basis) before partners become strongly tied to one another (i.e., within the first few months of “official” dating) and help people to avoid investing in relationships that they might later decide are wrong for them. Selection-based programs would intervene before an official dating relationship has formed, perhaps by helping people to identify especially compatible partners from within their network of friends and acquaintances. To develop such interventions, researchers must (a) identify when important relationship experiences (e.g., perceived responsiveness, capitalization, and sexual satisfaction) become reliably predictive of long-term outcomes and (b) identify how this information could be better incorporated into early relationship decisions. Overall, efforts to facilitate the initial formation and development of high-quality relationships may hold promising, untested potential.