Test–Retest Reliability in Automated Emotional Facial Expression Analysis: Exploring FaceReader 8.0 on Data from Typically Developing Children and Children with Autism

The nonverbal expression of guilt in healthy adults

Guilt is a negative emotion elicited by realizing one has caused actual or perceived harm to another person. One of guilt's primary functions is to signal that one is aware of the harm that was caused and regrets it, an indication that the harm will not be repeated. Verbal expressions of guilt are often deemed insufficient by observers when not accompanied by nonverbal signals such as facial expression, gesture, posture, or gaze. Some research has investigated isolated nonverbal expressions in guilt, however none to date has explored multiple nonverbal channels simultaneously. This study explored facial expression, gesture, posture, and gaze during the real-time experience of guilt when response demands are minimal. Healthy adults completed a novel task involving watching videos designed to elicit guilt, as well as comparison emotions. During the video task, participants were continuously recorded to capture nonverbal behaviour, which was then analyzed via automated facial expression software. We found that while feeling guilt, individuals engaged less in several nonverbal behaviours than they did while experiencing the comparison emotions. This may reflect the highly social aspect of guilt, suggesting that an audience is required to prompt a guilt display, or may suggest that guilt does not have clear nonverbal correlates.

Lighting environmental assessment in enclosed spaces based on emotional model

Lighting assessment in special operating environments like enclosed spaces is of great research significance and value. In addition to investigating the visual ergonomics of workers, the emotional monitoring and guidance of workers in enclosed spaces is also a research focus. Based on the Circumplex emotion model theory, this paper designs an experiment to assess emotions in an enclosed space with 6 different lighting settings (2 correlated color temperature (CCT) × 3 illuminance levels). From the perspective of subjective assessment, participants used a rapid sensory analysis method (Check-all-that-apply, CATA) and a Subjective Coordinate Scale (SCS) method for rapid ambience perception checking and emotional self-reporting of lighting settings. From the perspective of objective evaluation, the participants' facial expressions were recorded during the experiment using a camera, and then the recorded facial expressions were automatically analyzed and predicted using FaceReader (FRE) software. The CATA and SCS showed similar results, with the 3100 K × 600 lx, 3100 K × 1000 lx and 6500 K × 600 lx lighting settings creating a relaxed, pleasant emotion in participants, the 6500 K × 1000 lx setting creating an excited, tense atmosphere, and the low illumination level settings of 3100 K × 250 lx and 6500 K × 250 lx made participants feel tired and frustrated. The results of the objective emotion analysis indicate that the FRE was able to effectively identify differences in participants' emotions in response to different lighting settings and was consistent with the results of participants' subjective emotion reports. This laboratory study validates that the three methods can effectively assess the enclosed space lighting settings, and provides a reference for further research on the enclosed space lighting settings and emotional monitoring of workers in the future.