An open-source standardized pipeline for equitable observations of interactive behavioral dynamics: Theory-driven measurement, analysis, and masking.
American Psychologist · 2026-11 · 81 (8) · 1249-1264
DOI: 10.1037/amp0001718 ↗Kurz gefasst
Fachartikel in der Zeitschrift American Psychologist, 2026-11. Verfasst von Arkadiusz Białek und 7 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Psychology, Jagiellonian University. Hauptthemen laut MEDLINE: Behavior Observation Techniques, Social Interaction, Interpersonal Relations. Gefördert von: Strategic Program Excellence Initiative at the Jagiellonian University, Deutsche Forschungsgemeinschaft Visual Communication, Netherlands Organisation for Scientific Research.
Abstract (Originalsprache)
Behavioral observation has a long-standing tradition in psychology. However, its reliance on manual coding makes observational methods costly and prone to biases that arise from the inherent limits of coding schemes and from the subjectivity of human raters. Behavioral observation research therefore has drawbacks in terms of applicability, accessibility, reproducibility, and equitability. Computer vision (CV) methods have promise in this regard. In the context of quantifying human movement, CV approaches to pose estimation are becoming increasingly precise and have the benefit of being nonintrusive, reproducible, and low cost. With such methods, human movement in videos can be processed as multivariate time-series data, offering a basis for a more comprehensive analysis of individual, interpersonal, and social dynamics, opening up the possibility for the widespread study of diverse populations in out-of-lab real-world contexts. Fulfilling such a promise goes beyond technical progress, it requires a theory-driven implementation of new accessible observational methods made equitable to learn. To showcase this promise, we present a CV pipeline with analyses of the temporal dynamics of dyadic interactions, including a cross-cultural investigation of movement fluidity in sibling cooperation during task-focused interactions and longitudinal assessments of infant-caregiver coordination during free-play sessions. The pipeline incorporates a pedagogical computational notebook, pose estimation (YOLOv8), theory-driven linear and nonlinear time-series analysis, and a CV method for more privacy-aware video data archiving. Together, this pipeline showcases a promising advancement in behavioral observation methods, expanding both who can conduct research and who can benefit from it. (PsycInfo Database Record (c) 2026 APA, all rights reserved).
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Institute of Psychology, Jagiellonian University.
- Department of Computational Cognitive Science, Tilburg University.
- Institute for Logic, Language and Computation, University of Amsterdam.
- Behavioral Science Institute, Radboud University.
- Artificial Intelligence and Intelligent Systems, Hasso Plattner Institute.
ORCID-Profile: Arkadiusz Białek, Wim Pouw, James Trujillo, Fred Hasselman, Babajide Alamu Owoyele, Natalia Siekiera, Joanna Rączaszek-Leonardi, Travis J Wiltshire
Förderung
- Strategic Program Excellence Initiative at the Jagiellonian University
- Deutsche Forschungsgemeinschaft Visual Communication
- Netherlands Organisation for Scientific Research
Zitieren
APA
Białek, A., Pouw, W., Trujillo, J., Hasselman, F., Owoyele, B. A., Siekiera, N., Rączaszek-Leonardi, J., & Wiltshire, T. J. (2026). An open-source standardized pipeline for equitable observations of interactive behavioral dynamics: Theory-driven measurement, analysis, and masking. American Psychologist, 81(8), 1249-1264. https://doi.org/10.1037/amp0001718
Vancouver
Białek A, Pouw W, Trujillo J, Hasselman F, Owoyele BA, Siekiera N, et al. An open-source standardized pipeline for equitable observations of interactive behavioral dynamics: Theory-driven measurement, analysis, and masking. American Psychologist. 2026;81(8):1249-1264. doi:10.1037/amp0001718
BibTeX
@article{Biaek2026,
author = {Białek, Arkadiusz and Pouw, Wim and Trujillo, James and Hasselman, Fred and Owoyele, Babajide Alamu and Siekiera, Natalia and Rączaszek-Leonardi, Joanna and Wiltshire, Travis J},
title = {An open-source standardized pipeline for equitable observations of interactive behavioral dynamics: Theory-driven measurement, analysis, and masking},
journal = {American Psychologist},
year = {2026},
volume = {81},
number = {8},
pages = {1249--1264},
doi = {10.1037/amp0001718}
}
EUVIMED