Cultural differences in vocal emotion recognition: a behavioural and skin conductance study in Portugal and Guinea-Bissau

Abstract

Cross-cultural studies of emotion recognition in nonverbal vocalizations not only support the universality hypothesis for its innate features, but also an in-group advantage for culture-dependent features. Nevertheless, in such studies, differences in socio-economic-educational status have not always been accounted for, with idiomatic translation of emotional concepts being a limitation, and the underlying psychophysiological mechanisms still un-researched. We set out to investigate whether native residents from Guinea-Bissau (West African culture) and Portugal (Western European culture)-matched for socio-economic-educational status, sex and language-varied in behavioural and autonomic system response during emotion recognition of nonverbal vocalizations from Portuguese individuals. Overall, Guinea-Bissauans (as out-group) responded significantly less accurately (corrected p < .05), slower, and showed a trend for higher concomitant skin conductance, compared to Portuguese (as in-group)-findings which may indicate a higher cognitive effort stemming from higher difficulty in discerning emotions from another culture. Specifically, accuracy differences were particularly found for pleasure, amusement, and anger, rather than for sadness, relief or fear. Nevertheless, both cultures recognized all emotions above-chance level. The perceived authenticity, measured for the first time in nonverbal cross-cultural research, in the same vocalizations, retrieved no difference between cultures in accuracy, but still a slower response from the out-group. Lastly, we provide-to our knowledge-a first account of how skin conductance response varies between nonverbally vocalized emotions, with significant differences (p < .05). In sum, we provide behavioural and psychophysiological data, demographically and language-matched, that supports cultural and emotion effects on vocal emotion recognition and perceived authenticity, as well as the universality hypothesis.

Fig. 1

Presentation of the emotion authenticity and emotion recognition tasks. Both tasks had an inter-trial interval of 6 s followed by a nonverbal emotional vocalization presentation. Then, for the first task, participants rated the authenticity of the stimuli in a Likert scale 1–7, whereas for the second task, participants were asked to choose which of 6 emotions (or ‘other’) they recognized

Fig. 2

Main effects of nationality on accuracy (left) and response latency (middle) of the emotion recognition task, and on the response latency of the emotion authenticity task (right), with distribution (box plots) and mean values (cross) for each nationality (Guinea–Bissauan—GB, and Portuguese—PT). Only statistically significant main effects of nationality (at an FDR corrected p < .05) are shown

Fig. 3

Main effects of emotion, on the accuracy (top left) and response latency (top right) of the emotion recognition task, on the rating (bottom left) and response latency (bottom right) of the authenticity recognition task, and on the SCR amplitude (middle left) and latency (middle right) during the emotion recognition task, with distribution (box plots) and mean values (cross) for each emotion (amusement, pleasure, relief, sadness, anger, and fear). Each line represents a statistically significant comparison (at an FDR corrected p < .05 for behavioural measures and at an uncorrected p < .05 for physiological measures) between emotions. Only statistically significant main effects of emotion (at an FDR corrected p < .05 for behavioural measures and at an uncorrected p < .05 for physiological measures) are shown

Fig. 4

‘Emotion × nationality’ interaction effects on the accuracy (top left), response latency (top right) and concomitant SCR latency (bottom), for each emotion (amusement, pleasure, relief, sadness, anger, and fear) and nationality (Guinea–Bissauan and Portuguese), with distribution (box plots) and mean values (cross). Statistically significant post hoc comparisons (at an FDR corrected p < .05 for behavioural measures and at an uncorrected p < .05 for physiological measures) are marked as lines if between emotions and asterisks if between nationalities. Only statistically significant ‘emotion x nationality’ interaction effects (at an FDR corrected p < .05 for behavioural measures and at an uncorrected p < .05 for physiological measures) are shown