Predicting subjective rage and facial expressions in human driving: A Bayesian network approach with beta-distributed nodes

2026-07-20

AI Summary

This study addresses the challenge of modeling continuous, subjectively driven anger during driving and its relationship with facial expressions by proposing a novel Bayesian network framework. For the first time, it incorporates conditional Beta distribution nodes to enable fully Bayesian modeling of continuous emotion intensity constrained to the unit interval, effectively capturing conditional dependencies among variables and propagating uncertainty. Inference is implemented via Markov chain Monte Carlo (MCMC) methods in WinBUGS, allowing accurate prediction of anger intensity from facial action units. Empirical results reveal a significant positive association between brow furrowing and anger intensity—more frequently exhibited by males—and a reduction in upper eyelid raising under provocation, thereby validating both the methodological efficacy and behavioral insights of the proposed approach.

Abstract

A Bayesian network framework is proposed for modelling unit-bounded continuous variables using conditional beta-distributed nodes within a fully Bayesian inference setting. The model captures conditional dependencies and propagates uncertainty through the network, with inference performed via Markov Chain Monte Carlo methods implemented in WinBUGS. The framework is applied to an experimental study of emotional and facial responses, focusing on rage intensity and facial gestures. Results show that brow lowering is strongly associated with rage intensity and is more frequent in men, whereas upper lid raising decreases under provocation independently of rage or sex. The model also predicts rage severity from informative facial gestures.

Problem

• subjective rage
• facial expressions
• driving emotion
• beta-distributed variables
• Bayesian network

Innovation

• Bayesian network
• beta-distributed nodes
• facial expression
• subjective rage
• Markov Chain Monte Carlo