Detection and Recognition of Fearful Facial Expressions During the Coronavirus Disease (COVID-19) Pandemic in an Italian Sample: An Online Experiment

Abstract

In this observational study, the psychological ability to recognize the others' fearful expressions in Italian individuals during the pandemic COVID-19 lockdown was explored through a behavioral task performed online. An implicit version of the traditional facial emotion recognition task, grounded on the attentional and unconscious mechanism of the redundant target effect, was used. The experiment was scripted through the free software OpenSesame (Mathôt et al., 2012) and published on the Internet through the free software Jatos (Lange et al., 2015). The Reaction Time and level of Accuracy in detecting fearful expressions were computed. Overall, the data of 86 Italian individuals were collected. When their performance was scored in terms of Reaction Time, the redundant target effect did not emerge; instead, the expected effect was observed when the level of Accuracy was considered. Overall, the performance registered in this Italian sample in terms of accuracy was in line with previous results reported in Scarpina et al. (2018), in which a long extended version of the same behavioral task was used in a traditional experimental setting. This study might offer some considerations regarding the adoption of online experiments - together with self-report surveys - to assess the psychological and behavioral functioning during social restriction measures.

Keywords: COVID-19; facial emotion recognition; fear; implicit behavior; online assessment; social cognition.

FIGURE 1

Schematic representation of the attentional mechanism of the redundant target effect. For each experimental condition, an example of the visual stimulus was shown. According to the effect, participants would be faster (left arrow) and more accurate (right arrow) to provide their answer in the single and congruent conditions, in comparison with the emotional incongruent and neutral incongruent conditions, in which they were generally slower and less accurate.

FIGURE 2

Implicit facial emotion recognition task. (A) For each experimental condition (x-axis: single, congruent, emotional incongruent, neutral incongruent), the mean of Reaction Time expressed in millisecond (y-axis – ms) was reported. The minimum, the lower quartile, the median, the upper quartile, the maximum, and the outliers were shown. According to the main analyses, no difference emerged between the experimental conditions. (B) For each experimental condition (x-axis: single, congruent, emotional incongruent, neutral incongruent), the mean of the level of Accuracy expressed in percentage (y-axis – %) was shown. Again, the minimum, the lower quartile, the median, the upper quartile, the maximum, and the outliers were shown. According to the main analyses, significant differences emerged between conditions, mirroring the redundant target effect.

FIGURE 3

Comparison with the data reported in Scarpina et al. (2018). (A) The mean (lines) and standard error (vertical lines) relative to Reaction Time expressed in milliseconds (y-axis – ms) for each experimental condition (x-axis: single, congruent, emotional incongruent, neutral incongruent) was reported for the sample (n = 86) of the present experiment (dark gray lines) and the sample (n = 20) in Scarpina et al. (2018) (light gray lines). (B) The mean (bars) and the standard error (vertical lines) relative to the level of Accuracy expressed in percentage (y-axis – %) for each experimental condition (x-axis: single, congruent, emotional incongruent, neutral incongruent) were reported for the sample (n = 86) of the present experiment (dark gray bars) and the sample (n = 20) in Scarpina et al. (2018) (light gray bars).