Comparing, Differentiating, and Applying Affective Facial Coding Techniques for the Assessment of Positive Emotion

Cross, Marie P.; Hunter, Judy; Smith, Jayson R.; Twidwell, Robert E.; Pressman, Sarah D.

doi:10.1080/17439760.2022.2036796

Cited by 12 publications

(4 citation statements)

References 100 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are potential weaknesses in the usage of the Facial Action Coding System (FACS), particularly automated systems as was used in this study. Because of the reliance on an algorithm to generate the AUs, elements of the videos themselves, such as quality, lighting, colour, and angle, as well as of the individual in the video, such as hair length or position, glasses, piercings, or head scarves, can all greatly impact the ability of the system to correctly classify AUs 66 , 67 . Similarly, studies have found that the underlying algorithm has not been well trained on non-Western faces, meaning that the system does more poorly when attempting to analyze racialized groups 68 , 69 .…”

Section: Discussionmentioning

confidence: 99%

The nonverbal expression of guilt in healthy adults

Stewart,

Mitchell,

MacDonald

et al. 2024

Sci Rep

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 99%

The nonverbal expression of guilt in healthy adults

Stewart,

Mitchell,

MacDonald

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Finally, we used Noldus FaceReader ( www.noldus.com ) to obtain frame-by-frame estimates of social behaviour in terms of Facial Action Coding Unit (FACS) “action units” [ 70 ]. Although FaceReader reduces coding times dramatically, it is slightly less accurate than a well-trained human FACS coder and outputs behaviour codes at only 15 frames-per-second, so each frame summarizes data over 66.7ms [ 71 , 72 ].…”

Section: Discussionmentioning

confidence: 99%

The subjective value of genuine smiles guides real-world social behaviour

Heerey,

Clerke,

Johnson

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

The mechanisms that underpin human social behaviour are poorly understood, in part because natural social behaviour is challenging to study. The task of linking the mechanisms thought to drive social behaviour to specific social behaviours in a manner that maintains ecological validity poses an even greater challenge. Here we report evidence that the subjective value people assign to genuine smiles, as measured in the laboratory, determines their responsiveness to genuine smiles encountered in a naturalistic social interaction. Specifically, participants (university undergraduates; age 17 to 36) who valued genuine smiles to a greater degree also showed stronger attention capture effects to neutral faces that were previously associated with genuine smiles and faster reciprocity of a social partner’s smiles in a real social interaction. Additionally, the faster participants responded to the partner’s genuine smiles the higher the partner’s ratings of interaction quality were after the interaction. These data suggest that individual differences in subjective value of genuine smiles, measured in the lab, is one element that underpins responsiveness to natural genuine smiles and subsequent social outcomes.

show abstract

“…nveAI are objective markers of psychotic symptoms that can complement clinician ratings. They can be easily implemented as they do not required extensive training nor time-consuming coding (Cross et al, 2022). Thus, nveAI can facilitate research because it can capture nuances of facial expressions while maximizing efficiency and minimizing potential biases (Hamm et al, 2011;Wang et al, 2008).…”

Section: Discussionmentioning

confidence: 99%

Behavioral Markers of Psychotic Disorders: Using Artificial Intelligence to Detect Nonverbal Expressions in Video

Martin¹,

Lian²,

Oltmanns³

et al. 2022

Preprint

View full text Add to dashboard Cite

Emotional deficits in psychosis are prevalent and difficult to treat. In particular, much remains unknown about facial expression abnormalities, and a key reason is that expressions are very labor-intensive to code. Artificial intelligence measures of non-verbal expressions (nveAI) can remove this barrier. The current study sought to increase understanding of facial expression abnormalities in psychotic disorders by using nveAI. Changes of facial expressions and head position of participants—39 with schizophrenia/schizoaffective disorder (SZ), 46 with other psychotic disorders (OP), and 108 never psychotic individuals (NP)—were assessed via FaceReader, a commercially available automated facial expression analysis software, using video recorded during a clinical interview. We first examined the behavioral markers of the psychotic disorder groups and tested if they can discriminate between the groups. Next, we evaluated links of behavioral markers with clinical features (symptoms, functioning, and physical performance) controlling for group membership. We found the SZ group was characterized by significantly less variation in neutral expressions, happy expressions, arousal, and head orientation compared to NP. These markers discriminated SZ from NP well (AUC=.79, sensitivity=.79, specificity=.67) but discriminated SZ from OP less well (AUC=.66, sensitivity=.77, specificity=.46). We also found significant correlations between clinical features and all behavioral markers (particularly happy expressions, arousal, and head orientation), except disgust. Taken together, these results suggest that nveAI can provide useful behavioral markers of psychosis, which could improve research on non-verbal expressions in psychosis and, ultimately, enhance treatment.

show abstract

Comparing, Differentiating, and Applying Affective Facial Coding Techniques for the Assessment of Positive Emotion

Cited by 12 publications

References 100 publications

The nonverbal expression of guilt in healthy adults

The nonverbal expression of guilt in healthy adults

The subjective value of genuine smiles guides real-world social behaviour

Behavioral Markers of Psychotic Disorders: Using Artificial Intelligence to Detect Nonverbal Expressions in Video

Contact Info

Product

Resources

About