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 ↗At a glance
Journal article in American Psychologist, 2026-11. Written by Arkadiusz Białek and 7 co-authors. Institution: Institute of Psychology, Jagiellonian University. Major MEDLINE topics: Behavior Observation Techniques, Social Interaction, Interpersonal Relations. Funded by: Strategic Program Excellence Initiative at the Jagiellonian University, Deutsche Forschungsgemeinschaft Visual Communication, Netherlands Organisation for Scientific Research.
Abstract (original language)
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).
Subjects
MeSH terms (MEDLINE)
Authors and institutions
- 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 profiles: Arkadiusz Białek, Wim Pouw, James Trujillo, Fred Hasselman, Babajide Alamu Owoyele, Natalia Siekiera, Joanna Rączaszek-Leonardi, Travis J Wiltshire
Funding
- Strategic Program Excellence Initiative at the Jagiellonian University
- Deutsche Forschungsgemeinschaft Visual Communication
- Netherlands Organisation for Scientific Research
Cite
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