EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Detecting Young Children's Deception Using Facial Expression Analysis With High Dimensional Statistical Methods

Wanjie Wang, Xiao Pan Ding, Xinran Zhang, Meng Dai

Developmental Science · 2026

DOI: 10.1111/desc.70263 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Developmental Science, 2026. Verfasst von Wanjie Wang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Statistics and Data Science, National University of Singapore, Singapore. Hauptthemen laut MEDLINE: Facial Expression, Deception. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National University of Singapore (NUS) Start-up Grant, the NUS Centre for Family and Population Research Faculty Development Grant.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Although deception is common in early childhood, accurately detecting deception remains a significant challenge. The present study aims to investigate the feasibility of using high‐dimensional statistical methods to detect children's deception through facial expressions, with a focus on incorporating two time‐dependent statistics: slope and fitness. We analyzed the facial expressions of 93 three‐ to six‐year‐old children during a guessing game. A machine vision algorithm (FACET) assessed the likelihood of nine basic facial expressions. We extracted three statistics (mean, slope and fitness) for each facial expression. Then, we used high‐dimensional feature selection method to filter out irrelevant features. We adopted two parametric (logistic regression, linear discriminant analysis) and two non‐parametric statistical methods (random forest, adaptive boosting) and tested both the full feature set (“full model”) and the selected feature set (“2‐step model”). The results showed adding time‐dependent statistics (slope and fitness) improved performance, with the average balanced accuracy increasing from 47.2% to 62.0%. Feature selection further enhanced the model performance (from 60.8% to 63.3%). In addition, balanced accuracy provided a more conservative and reliable measure than the original accuracy (54.6% vs. 61.5%). These findings demonstrate the feasibility of using dynamic facial emotional features to detect deception in early childhood and highlight the potential of computational methods for advancing developmental research on emotion and social cognition.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Facial ExpressionDeceptionHumansChildFemaleChild, PreschoolMaleAlgorithms

Stichwörter der Autor:innen

adaptive boostingdetecting deceptionfacial expressionfeature selectionlinear discriminant analysislogistic regressionrandom forest

Autor:innen und Institutionen

  • Department of Statistics and Data Science, National University of Singapore, Singapore.
  • Department of Psychology, National University of Singapore, Singapore, Singapore.

Förderung

  • National University of Singapore (NUS) Start-up Grant
  • the NUS Centre for Family and Population Research Faculty Development Grant

Zitieren

APA

Wang, W., Ding, X. P., Zhang, X., & Dai, M. (2026). Detecting Young Children's Deception Using Facial Expression Analysis With High Dimensional Statistical Methods. Developmental Science. https://doi.org/10.1111/desc.70263

Vancouver

Wang W, Ding XP, Zhang X, Dai M. Detecting Young Children's Deception Using Facial Expression Analysis With High Dimensional Statistical Methods. Developmental Science. 2026. doi:10.1111/desc.70263

BibTeX
@article{Wang2026,
  author = {Wang, Wanjie and Ding, Xiao Pan and Zhang, Xinran and Dai, Meng},
  title = {Detecting Young Children's Deception Using Facial Expression Analysis With High Dimensional Statistical Methods},
  journal = {Developmental Science},
  year = {2026},
  doi = {10.1111/desc.70263}
}
Kostenlos starten →