EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Regularized Multilevel Multinomial Regression for Select-All-That-Apply Responses and High-Dimensional Predictors with Applications to Perception of Facial Expressions

Nathaniel E Helwig iD, Keding Chen, Stephen J Guy, Sofia Lyford-Pike

Psychometrika · 2026-06 · 91 (3) · 868-888

DOI: 10.1017/psy.2026.10102 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Psychometrika, online erschienen am 22.04.2026. Verfasst von Nathaniel E Helwig und 3 weiteren Autor:innen. Beteiligte Einrichtung: Psychology and Statistics, https://ror.org/017zqws13University of Minnesota Twin Cities, USA. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This article develops an analysis pipeline for quantifying and relating mouth shape variation to the emotions perceived from facial expressions. We use open-source data that contains ratings from 802 fairgoers on 27 smile-like expressions. Each rater was given a list of seven emotions (happy, sad, anger, contempt, fear, surprise, and disgust) and asked to select all of the words that best described the facial expression. To develop a generalizable method for quantifying mouth shape variation, we leverage statistical shape analysis techniques to parameterize each mouth’s shape in terms of 30 systematically placed landmarks that outline the upper and lower lips. Furthermore, we demonstrate that a three-dimensional representation of these landmark coordinates produces an interpretable feature set that outperforms the original and full-dimensional feature sets in terms of predictive performance. To connect the mouth shape features to the emotion ratings, we develop a nonparametric multinomial regression model that is capable of shrinkage and selection with high-dimensional predictors. Our results demonstrate that the proposed method can produce easily interpretable model predictions that enhance our understanding of the nature in which subtle variations in mouth shape affect the perception of a facial expression.

Schlagwörter

Stichwörter der Autor:innen

dimension reductionnonparametric regressionpenalized regressionshape analysissmile perception

Autor:innen und Institutionen

  • Psychology and Statistics, https://ror.org/017zqws13University of Minnesota Twin Cities, USA.
  • Psychology, https://ror.org/017zqws13University of Minnesota Twin Cities, USA.
  • Computer Science & Engineering, https://ror.org/017zqws13University of Minnesota Twin Cities, USA.
  • Otolaryngology-Head & Neck Surgery, https://ror.org/017zqws13University of Minnesota Twin Cities, USA.

ORCID-Profile: Nathaniel E Helwig

Zitieren

APA

Helwig, N. E., Chen, K., Guy, S. J., & Lyford-Pike, S. (2026). Regularized Multilevel Multinomial Regression for Select-All-That-Apply Responses and High-Dimensional Predictors with Applications to Perception of Facial Expressions. Psychometrika, 91(3), 868-888. https://doi.org/10.1017/psy.2026.10102

Vancouver

Helwig NE, Chen K, Guy SJ, Lyford-Pike S. Regularized Multilevel Multinomial Regression for Select-All-That-Apply Responses and High-Dimensional Predictors with Applications to Perception of Facial Expressions. Psychometrika. 2026;91(3):868-888. doi:10.1017/psy.2026.10102

BibTeX
@article{Helwig2026,
  author = {Helwig, Nathaniel E and Chen, Keding and Guy, Stephen J and Lyford-Pike, Sofia},
  title = {Regularized Multilevel Multinomial Regression for Select-All-That-Apply Responses and High-Dimensional Predictors with Applications to Perception of Facial Expressions},
  journal = {Psychometrika},
  year = {2026},
  volume = {91},
  number = {3},
  pages = {868--888},
  doi = {10.1017/psy.2026.10102}
}
Kostenlos starten →