EUVIMEDEUVIMED entdecken
Crossref

Predicting Dyadic Synchrony: A Theory‐Driven Machine Learning Approach

Michel Sfeir iD, Fabiola Silletti iD, Hung-Chu Lin, Ga Tin Finneas Wong, Candice Ma, Chloe Bancel, Emma Clark, Leena Mittal, Carmina Erdei, Joshua Roffman, Mélanie De Leener, Mandy Rossignol und 2 weitere

Infancy · 2026-05 · 31 (3)

DOI: 10.1111/infa.70092 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Infancy, online erschienen am 15.05.2026. Verfasst von Michel Sfeir und 13 weiteren Autor:innen. Beteiligte Einrichtung: Department of Clinical Psychology, University of Mons, Mons, Belgium. Hauptthemen laut MEDLINE: Machine Learning, Mother-Child Relations. Die Arbeit nennt 76 Literaturangaben. Gefördert von: NIMH NIH HHS, Fonds De La Recherche Scientifique-FNRS, National Institute of Mental Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Dyadic synchrony, defined as the coordination of emotional and behavioral signals between mother and child, is a central mechanism supporting early socioemotional development. However, predicting its emergence remains challenging because relational and psychological influences may combine in complex, context‐sensitive ways that are not easily captured by traditional linear models. The present study applied a theory‐guided machine learning approach to examine predictors of observed synchrony in 204 mother–child dyads (mean maternal age = 33.7 years, 89% White, 52.6%, boys mean children's age = 11.71 months), drawn from the PEACE (Perinatal Experiences and COVID‐19 Effects) Study, with data collected between November 2021 and August 2022. Dyadic synchrony and affective behaviors were coded from free‐play interactions using the Coding Interactive Behavior system, and psychological predictors included maternal anxiety, resilience, parenting stress, and observed affective expressions. Random Forest models were compared with linear regression, and model interpretation was supported using SHAP and ALE techniques. Linear regression showed slightly stronger predictive performance, whereas Random Forest revealed potentially meaningful non‐linear and interaction‐based patterns. In particular, synchrony tended to decrease under conditions reflecting imbalance between parenting stress and child positive affect, and affective mismatch showed a non‐monotonic association with synchrony. These findings highlight the context‐dependent nature of dyadic coordination and suggest that synchrony may emerge from configurations of stress, affect, and emotional alignment rather than from simple additive effects. More broadly, the study illustrates how interpretable machine learning can complement traditional statistical models to explore complex relational processes in early development.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningMother-Child RelationsHumansFemaleMaleAdultPredictive Learning ModelsRandom ForestChild, PreschoolEmotionsPrediction Algorithms

Stichwörter der Autor:innen

developmentemotionsfamily relationshipsmachine learningsynchrony

Autor:innen und Institutionen

  • Department of Clinical Psychology, University of Mons, Mons, Belgium.
  • The Distress Lab, University of Mons, Mons, Belgium.
  • Department of Psychology and Health Sciences, Pegaso University, Naples, Italy.
  • Department of Education, Psychology, Communication, University of Bari Aldo Moro, Bari, Italy.
  • Department of Pediatrics, Division of Newborn Medicine, Brigham and Women's Hospital, Boston, Massachusetts, USA.
  • Department of Psychology, University of Louisiana at Lafayette, Lafayette, Louisiana, USA.

ORCID-Profile: Michel Sfeir, Fabiola Silletti

Förderung

  • NIMH NIH HHS
  • Fonds De La Recherche Scientifique-FNRS
  • National Institute of Mental Health
  • Fonds De La Recherche Scientifique - FNRS

Zitieren

APA

Sfeir, M., Silletti, F., Lin, H. C., Wong, G. T. F., Ma, C., Bancel, C., Clark, E., Mittal, L., Erdei, C., Roffman, J., De Leener, M., Rossignol, M., Galdiolo, S., & Liu, C. (2026). Predicting Dyadic Synchrony: A Theory‐Driven Machine Learning Approach. Infancy, 31(3). https://doi.org/10.1111/infa.70092

Vancouver

Sfeir M, Silletti F, Lin HC, Wong GTF, Ma C, Bancel C, et al. Predicting Dyadic Synchrony: A Theory‐Driven Machine Learning Approach. Infancy. 2026;31(3). doi:10.1111/infa.70092

BibTeX
@article{Sfeir2026,
  author = {Sfeir, Michel and Silletti, Fabiola and Lin, Hung-Chu and Wong, Ga Tin Finneas and Ma, Candice and Bancel, Chloe and Clark, Emma and Mittal, Leena and Erdei, Carmina and Roffman, Joshua and De Leener, Mélanie and Rossignol, Mandy and Galdiolo, Sarah and Liu, Cindy},
  title = {Predicting Dyadic Synchrony: A Theory‐Driven Machine Learning Approach},
  journal = {Infancy},
  year = {2026},
  volume = {31},
  number = {3},
  doi = {10.1111/infa.70092}
}
Kostenlos starten →