Tag

facial expression

Browsing

Friends of the Nonverbal Communication Blog, this week we present the paper “Racial Identity-Aware Facial Expression Recognition Using Deep Convolutional Neural Networks”, by Sohail, M.; Ali, G.; Rashid, J.; Ahmad, I.; Almotiri, S. H.; AlGhamdi, M. A.; Nagra, A. A. and Masood, K. (2021), in which authors investigate the possibility of including, thanks to a software, the ability to consider ethnic groups when it comes to analyzing facial expressions. 

Because manual analysis of facial expression is sometimes kind of time-consuming, different software is being used more and more to automate the process. However, authors wonder, do they consider the differences between ethnic groups and their faces?

The objective of a facial expression recognition system is to recognize the emotions that they show, because there are a series of muscular movements of the face that are associated with certain emotions and can make us infer what a person feels.

These emotions are usually happiness, sadness, surprise, anger, fear and disgust, although contempt or neutral expression are sometimes included.

Although many studies have focused on facial expression recognition using static images, this can be very difficult for three reasons, as authors explain.

First, because the variations in facial structure between subjects from different cultures make the classification task pretty complex in some cases.

Second, because the similarity between expressions may be significant, and therefore a challenge to recognize each one accurately.

Lastly, different subjects may present variations in the expression of their emotions due to their facial appearance and their biometric forms.

In general, authors consider that the variability of facial structure between cultures could lead to incorrect recognition of facial expression because the image of an emotion in one culture may be different from the image of the same emotion in another culture. For example, it is known that members of different cultures can express levels of arousal to an emotion that won’t appear in another culture.

Therefore, authors believe that including a description of racial identity in automated facial recognition software models would make the process more reliable.

Specifically, authors develop in this work a new deep learning technique: the Racial Identity Aware Network (RIA-Net) learns facial expressions from images and extracts racial identity features from a previously trained racial identity network (RI-Net). -Net). The latter is trained using multicultural data from Japanese, Taiwanese, American, Caucasian, Moroccan people…

In addition, they use a model based on convolution neural networks, which has previously been successfully used by experts such as Pons and Masip, for facial expression recognition.

Authors think that it is very important to consider ethnic. It has been shown that the representation of facial expression is not only influenced by muscular deformation of the facial structure, but also by many other social factors such as culture, geography, or ethnic group.

How was the study carried out? Well, a recognition system for facial expressions associated with seven emotions was proposed. It knew sadness, happiness, anger, fear, surprise, disgust and neutral emotion.

Then, five different cultures were considered: Moroccan, Caucasian, Taiwanese, American and Japanese. To do this, images from country-specific databases with faces of native people were extracted.

The findings show, in the first place, that the highest percentage of misunderstanding arises among the emotions of anger, sadness and fear, the opposite occurring with happiness and surprise, where there were 100% correct answers.

The proposed method achieved an accuracy of 97%. Under the same conditions, without using racial identity traits, the accuracy dropped to 93.28%. These results show that the use of racial identity traits in the recognition of facial expressions significantly improves the results.

The current pandemic situation has made online communication much more common. In addition, globalization has facilitated communication between people from different parts of the world and, therefore, different cultures. Facial expressions play a very important role in this regard, so it is especially important to pay attention to multiculturalism when it comes to identifying emotions through the face.

If you want to know more about nonverbal behavior and how it influences our personal relationships, visit our Nonverbal Communication Certificate, a 100% online program certificated by the Heritage University (Washington) with special discounts for readers of the Nonverbal Communication Blog.

Friends of the Nonverbal Communication Blog, this week we present the paper “Reading and reacting to faces, the effect of facial mimicry in improving facial emotion recognition in individuals with antisocial behavior and psychopathic traits”, by Kyranides, M. N.; Petridou, M.; Gokani, H. A.; Hill, S. and Fanti, K. A. (2022), in which authors investigate how people with antisocial personality disorder and/or psychopathic personality disorder recognize and answer to facial expressions.

Both antisocial personality disorder and psychopathy are associated with severe antisocial traits.

Antisocial personality disorder (APD from now on) has an identity of its own, and by many intellectuals, psychopathy is considered as part of it. However, other experts believe that psychopathy can be considered as a personality itself, and not as a behavioral trait.

Psychopathy, as we have already explained, would include the traits of the dark triad, which encompasses affective, interpersonal, and behavioral characteristics.

Correctly interpreting and transmitting affective and emotional states is crucial for social relationships and healthy group functioning of human beings.

Facial expressiveness plays a central role in interpersonal relationships, as it communicates silent social cues and helps reinforce acceptable social behaviors. In addition, it is a non-verbal channel that we pay a lot of attention to.

Previous studies suggest that people with psychopathic traits are characterized by deficiencies in facial emotion recognition, which, in turn, results in poor social adaptation and dysfunctional interpersonal relationships.

This raises the idea that similar deficits seen in people with antisocial personality disorder are due to the disorder itself or are the result of psychopathic features, although whether the latter are part of the antisocial disorder is unclear.

This week’s study aimed to differentiate the emotion-processing deficits of individuals with these traits, by examining how people with antisocial personality disorder, people with psychopathic disorder, and people with both, identify affective facial expressions and how they obey the instructions in which they are asked to imitate these expressions.

Empirical evidence suggests that people with psychopathic traits will show deficiencies in emotion recognition, but especially in facial expressions of fear and sadness.

Regarding antisocial personality disorder, very few people have explored the matter. In a 2014 study, more severe deficiencies in disgust recognition were found in a sample of people with APD compared to the control group. In 2002, deficiencies in the correct identification of happy and sad facial expressions were found, but no study controlled the psychopathic features that appeared in subjects with APD.

If these people theoretically experience difficulties in identifying the emotions of others, would they be capable of practicing facial mimicry?

Individuals with typical personality development engage in facial mimicry automatically when observing the expressions of others, and this has been associated with empathy.

However, the findings regarding facial mimicry in individuals with psychopathic traits are diverse. For example, according to one study, they have intact the ability to accurately mimic the expression of fear; according to another, they have difficulty reflecting negative emotions.

Something that seems to be logical is that if people with psychopathic traits and people with TPA have deficits in their ability to be empathic, they will have some kind of difficulty in correctly imitating the emotions of others. But, as we see, it is something that seems not to be confirmed.

For this study, 107 people over 18 years old were gathered, who were evaluated individually. They were presented with dynamic stimuli of facial expressions of sadness, happiness, anger, fear, and pain, in addition to neutral expressions. They had to imitate the presented expressions, suppress any facial response elicited by the stimulus, or do nothing and only answer the question of what facial expression was being displayed.

The results showed that facial recognition accuracy was significantly worse in the group that had psychopathic traits and APD at the same time, compared to the control group. In addition, the psychopathic traits + APD group showed increased choice of angry facial expression compared to the others. Surprisingly, the group that only had APD, showed more pronounced facial expressions when they had to mimic the expressions shown to them.

These findings are in line with previous work on the deficiencies of these people in the recognition of facial emotions and point towards the idea that the presence of psychopathic traits, isolated from antisocial personality, may represent a profile in itself, in which individuals would function in a similar way, but also different.

If you want to know more about nonverbal behavior and how it influences our personal relationships, visit our Nonverbal Communication Certificate, a 100% online program certificated by the Heritage University (Washington) with special discounts for readers of the Nonverbal Communication Blog.

Friends of the Nonverbal Communication Blog, this week we present the paper “Gender Biases in Estimation of Others’ Pain” by Zang, L.; Reynolds Losin, E. A.; Ashar, Y. K.; Koban, L. and Wager, T. D. (2021), where the authors carry out two experiments to know if women feel or express more pain than men, or if it happens the other way round. 

Accurately estimating the pain of others based on nonverbal signals is an essential aspect of interpersonal communication, since it is the basis of empathy and care.

Acknowledging the pain of others is an increasingly valuable interpersonal skill, both for doctors and for the rest of the population.

Although pain is usually assessed through self-reports, recognition of facial expressions of pain is a very important part of the assessment.

Because expressions of pain are communicative behaviors, observers’ interpretations of those expressions are a crucial aspect of pain communication. These interpretations are affected not only by the characteristics of the expressions of pain, but also by the observer’s knowledge and biases about pain and the characteristics of those who suffer from it.

For example, several studies have shown that psychological treatment is more likely to be recommended for women suffering any kind of pain than for men, who are prescribed painkillers. Therefore, female patients take longer to receive analgesic medication. However, it is important to note that there are other studies of gender bias in pain management that show the opposite pattern, or no significant gender difference.

Despite clinical evidence of underestimation and undertreatment of pain in female patients, laboratory results on gender bias have been inconsistent and, in fact, some studies have found that women felt more pain than men, having note their facial expressions.

That is, it seems that a large part of the results in the evaluation of pain is decided by facial expressions. Therefore, controlling the objective measures of facial expressiveness in general, and of pain in particular, is an important step in stopping the bias in the perceiver.

In this context, there are also gender stereotypes related to pain, for example, that women complain more than men and do not accurately report their pain, or that men are more sensible and when they complain about their pain, it is real. These beliefs would affect pain assessment and treatment.

To delve into the subject, authors conducted two experiments. First, they compared differences in pain estimation in men and women, controlling for the same level of facial expressiveness and also controlling for patients’ self-reported pain. This is necessary because the amount of pain patients experience is highly variable, also because the facial response to pain is one of the most salient cues we use to estimate pain, and lastly, because the expressiveness of patients can affect observer estimates through empathy.

For experiment 1, 50 volunteers participated and had to watch a series of videos of faces of people experiencing pain. Each video was coded through the FACS system, and the action units AU4 (lowering of the eyebrows), AU6 and 7 (contraction of the eyelids), AU9 and 10 (contraction of the elevator) and AU43 (closure of the eyes) were especially relevant. These action units are representative of the emotion of pain.

In addition, the videos included a self-report from the patients where they rated their own pain.

The objective of this experiment was to test whether the sex of the patients affects the estimation of pain according to the observers. The hypothesis was that if the intensity of facial expressions was not controlled, female patients would be perceived as being in more pain than male patients. If, on the other hand, there were similar levels of expression and self-reported pain, it would be the male patients who would be perceived as having more pain.

The results did not support the hypotheses. Male and female patients were not perceived to have different degrees of pain before controlling pain, facial expressiveness, and patient self-reported pain. However, female patients were perceived to have less pain than male patients when facial expressions and self-reports were controlled.

The second experiment was very similar, except that opinion questionnaires about pain treatment and gender stereotypes were added.

In general, women’s pain was underestimated relative to self-reported pain, while men’s was overestimated. In addition, female patients, according to observers, would benefit more from psychotherapy than male patients.

The underestimation of pain and psychologization in the treatment of women’s pain could have very negative side effects on their health. Therefore, the existence of these stereotypes must be taken into account and act accordingly, so that both men and women receive the treatment they need and their health is not harmed.

If you want to know more about nonverbal behavior and how it influences our personal relationships, visit our Nonverbal Communication Certificate, a 100% online program certificated by the Heritage University (Washington) with special discounts for readers of the Nonverbal Communication Blog.

NonVerbal Communication Blog