Asymmetries of influence: differential effects of body postures on perceptions of emotional facial expressions

Abstract

The accuracy and speed with which emotional facial expressions are identified is influenced by body postures. Two influential models predict that these congruency effects will be largest when the emotion displayed in the face is similar to that displayed in the body: the emotional seed model and the dimensional model. These models differ in whether similarity is based on physical characteristics or underlying dimensions of valence and arousal. Using a 3-alternative forced-choice task in which stimuli were presented briefly (Exp 1a) or for an unlimited time (Exp 1b) we provide evidence that congruency effects are more complex than either model predicts; the effects are asymmetrical and cannot be accounted for by similarity alone. Fearful postures are especially influential when paired with facial expressions, but not when presented in a flanker task (Exp 2). We suggest refinements to each model that may account for our results and suggest that additional studies be conducted prior to drawing strong theoretical conclusions.

Figure 1. Models of emotion perception.

The relative position of emotions as organized by (a) the Seed Model [13] and (b) the Dimensional model [3]. Reprinted from Aviezer, Hassin, Bentin, & Trope, 2008, Putting Facial Expressions Back in Context [13]. Copyright Guilford Press. Reprinted with permission of The Guilford Press.

Figure 2. Incongruent and congruent stimuli.

Examples of Congruent (fearful face on fear body) and Incongruent (fearful face on angry body; fearful face on sad body) stimuli from Experiments 1a and 1b. All expressions used in these studies were obtained from the NimStim face set [44] and all models provided consent for publication of the photos in publications and on the web. Models for body expressions have given written informed consent, as outlined in the PLOS consent form, to publication of their photograph.

Figure 3. Results for Experiment 1a.

a) Proportion of correct responses for each facial expression, presented by posture. b) Median reaction time results for each facial expression, presented by posture. Results are presented in milliseconds. c) Proportion of errors made for each facial expression, presented by posture. Dotted line represents the proportion of errors made by participants viewing congruent expressions, and was used as a baseline error level. * over individual bars indicate a significant difference between congruent and incongruent trials.

Figure 4. Results for Experiment 1b.

a) Proportion of correct responses for each facial expression, presented by posture. b) Median reaction time results for each facial expression, presented by posture. Results are presented in milliseconds. c) Proportion of errors made for each facial expression, presented by posture. Dotted line represents the proportion of errors made by participants viewing congruent expressions, and was used as a baseline error level. * over individual bars indicate a significant difference between congruent and incongruent trials.

Figure 5. Stimuli presented in flanker task.

Examples of Congruent (fearful body flanked by fearful bodies) and Incongruent (fearful body flanked by angry bodies) stimuli from Experiment 2.