Face the Truth: Interpretable Emotion Genuineness Detection

Cardaioli, Matteo; Miolla, Alessio; Conti, Mauro; Sartori, Giuseppe; Monaro, Merylin; Scarpazza, Cristina; Navarin, Nicolò

doi:10.1109/ijcnn55064.2022.9892298

Cited by 1 publication

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nowadays, a widespread criticism to Machine Learning (ML) algorithms is that they provide un-interpretable results (i.e., a percentage of classification accuracy without explaining the classification rules; see Carvalho et al, 2019 ). Recently, a paper tried to overcome this shortcoming by using interpretable ML models able to detect and describe differences between genuine and non-genuine emotional expressions ( Cardaioli et al, 2022 ). Interpretable ML models are algorithms that, besides providing the scientists with a classification accuracy, also identify facial movements that mostly contribute to the classification of genuine and posed emotions.…”

Section: Methodological Limitationsmentioning

confidence: 99%

“…Graphs report tree decision paths and feature thresholds to predict fake (F) and genuine (G) expressions. Image is modified from Cardaioli et al (2022) .…”

Section: Methodological Limitationsmentioning

confidence: 99%

“…Facial displays are not identical for different subjects, nor even for the same emotion ( Sadeghi et al, 2013 ; Sangineto et al, 2014 ; Durán et al, 2017 ). A recent paper ( Cardaioli et al, 2022 ) capitalized the PEDFE dataset described above ( Miolla et al, 2022 ). The PEDFE dataset is unique to explore inter-individual differences in emotional expression, as, besides including genuine and posed dynamic emotional expression, it also includes many emotional stimuli for each “actor,” where the same emotion is expressed with different intensities or response to different stimuli.…”

Section: Methodological Limitationsmentioning

confidence: 99%

See 2 more Smart Citations

What is missing in the study of emotion expression?

2023

Self Cite

View full text Add to dashboard Cite

While approaching celebrations for the 150 years of “The Expression of the Emotions in Man and Animals”, scientists’ conclusions on emotion expression are still debated. Emotion expression has been traditionally anchored to prototypical and mutually exclusive facial expressions (e.g., anger, disgust, fear, happiness, sadness, and surprise). However, people express emotions in nuanced patterns and – crucially – not everything is in the face. In recent decades considerable work has critiqued this classical view, calling for a more fluid and flexible approach that considers how humans dynamically perform genuine expressions with their bodies in context. A growing body of evidence suggests that each emotional display is a complex, multi-component, motoric event. The human face is never static, but continuously acts and reacts to internal and environmental stimuli, with the coordinated action of muscles throughout the body. Moreover, two anatomically and functionally different neural pathways sub-serve voluntary and involuntary expressions. An interesting implication is that we have distinct and independent pathways for genuine and posed facial expressions, and different combinations may occur across the vertical facial axis. Investigating the time course of these facial blends, which can be controlled consciously only in part, is recently providing a useful operational test for comparing the different predictions of various models on the lateralization of emotions. This concise review will identify shortcomings and new challenges regarding the study of emotion expressions at face, body, and contextual levels, eventually resulting in a theoretical and methodological shift in the study of emotions. We contend that the most feasible solution to address the complex world of emotion expression is defining a completely new and more complete approach to emotional investigation. This approach can potentially lead us to the roots of emotional display, and to the individual mechanisms underlying their expression (i.e., individual emotional signatures).

show abstract

Section: Methodological Limitationsmentioning

confidence: 99%

“…Graphs report tree decision paths and feature thresholds to predict fake (F) and genuine (G) expressions. Image is modified from Cardaioli et al (2022) .…”

Section: Methodological Limitationsmentioning

confidence: 99%