Today emotions play an increasingly important role in business. At some point people came to understand that the buyer makes a purchasing decision based not only on what he thinks about the product, but also on what he feels about him. That's why companies are actively trying to add an emotional aspect to their work: analytics, service, technology.
 
 
The era of emotionless rationalism came to an end for a man a long time ago, but for modern machines, the dawning of their emotional intelligence is now coming. Over the past ten years, we have seen the rapid development of emotional technologies, an area often referred to as "Affective Computing". But where there are emotions, there are always many mysteries.
 
 
Some erroneous clichés are encountered especially often. We will look at the three most popular emotion myths in Affective Computing, which are actively spreading in the business environment and the media space.
 
 
 
Denied the idea of ​​the universality of emotions . He believed that the relationship between a person and emotions is not as straightforward as Ekman originally believed, and emotions have a certain value depending on the context. Later, in her book Emotions and the Body, Beatriz de Gelder wrote that as a result of experiments with fMRI it was not possible to identify any neurological reasons for confirming the universality of certain emotions.
 
 
Not long ago, one of the most prominent critics of the theory of basic emotions, the famous neuroscientist Lisa Barrett said that emotions are not innate, but acquired through experience quality. Understanding emotions is different for different people and cultures. There is a series of Research , in which the scientific group went to Namibia to study how the tribe of the Himba hermits will recognize the joyful, sad, angry, frightened or neutral expressions of persons. With the perception of the manifestations of positive emotions did not arise, however, Himba often confused anger and disgust. Similar experiments in other tribes showed similar results. This allowed Barrett to conclude that our explanation and understanding of emotions is inherent in culture - we give similar names to things that in reality mean different concepts.
 
 
Despite the fact that in 2011 Ekman changed his definition of "emotions" by including cultural and individual aspects there, and even excluding one of the basic emotions, many companies still base their work in affective computations on the old theory. They still include the concept of "basic emotions" in their databases, and, like considers Lisa Barrett , it is this approach that will become their Achilles' heel. However, one adds, if we take into account the external and internal context, then this technology has great potential to make a revolution in the sphere of the science of emotions.
 
 
Laboratories and companies that work with emotional analytics should not understand emotions as something universal. First, affective datasets must be specific, because they are used to teach the algorithm, and therefore must include information about culture, language, gender and even age, to correctly identify the emotion. Secondly, algorithms for recognizing emotions should be receptive to the context. It is very important to note the fact that some laboratories tried to take into account the context (for example, here ), But no "big" company engaged in affective calculations has made such attempts yet.
 
 

Myth 2: Smile is an indicator of happiness

 
On the other hand, Ekman's theory led to a natural conclusion that the expressed emotion can be connected with the feelings that a person experiences.
 
For example, the smile that algorithms detect most easily can have different meanings: a sense of happiness, joy, satisfaction, support, etc. Hence the question arises: what is its function?
 
 
 
 
In a recent study[1]subjects were asked to do nine complex exercises that were displayed on the monitor. When the participants were able to give the correct answer to any of these difficult tasks, they were smiling, although they had only a computer screen in front of them. At the same time, the theory of social instruments ( social displays ) Argues that the function of a smile can vary depending on whether the person is alone or in a particular social environment.
 
 
In affective calculations, at least in their commercial version, modern technologies for recognizing emotions are able to analyze emotions only separately from the social context. So, in order to really understand the meaning of a smile, we must teach the machine to distinguish emotions in different situations, both social and not. There is a difference between how we smile when we are with someone and when a smile appears in front of the monitor. That is why one should approach the nature of emotions more seriously. Analysis of facial expressions can be carried out in conjunction with the addition of acoustic parameters, analysis of body movement or physiological characteristics - this approach is called the multimodality of emotions.
 
 

Myth 3: Language of the body?

 
So, we came to the conclusion that emotions are not universal, the concept of "basic emotions" is controversial, and the expression of emotions is directly related to the cultural, individual and contextual aspects. Since the expression of emotions is not limited to our face, but also includes voice, body movements, interpersonal distance and various physiological manifestations, the situation becomes more complicated.
 
 
 
 
Also, as people often people try to understand whether they are deceiving, they are looking at the person's face, they are watching over the body. Body movements have tried to connect with almost anything. The most famous options - a person touches his mouth when he lies, or takes an open pose when he feels calm and safe. This theory became so widespread that its echoes fell into the sphere of stress management, security issues and even cinema.
 
 
For example, airport security has always been a priority. The first automatic behavior detection systems (behavior detection systems) installed in US airports in the late 20th century. Since then, they have spread all over the world. Usually, the calculation of the probability of whether a passenger is potentially dangerous is based on taking into account key characteristics that are associated with high risk. To date, many scientists have argued that certain psychological personality traits that may be peculiar to terrorists have not been found.[2]Similarly, the correlation between how a person moves and whether he is lying at this moment is not as straightforward as people's psychology maintains.
 
 
The existence of a popular version of the "language" of the body revealing the true feelings of man is a more than controversial issue. Of course, we can make a connection between non-verbal signals and emotional behavior. To date, there is a whole technology of tracking body movements, body-tracking. In Affective Computing, tracking is used to collect statistics on the relationship between movements and certain emotions.
 
 

In conclusion,

 
Affective computing is an amazing but complex field, both for science and business. It is truly on the edge of high technology. However, in many cases, the approach to using emotion recognition technologies in commerce is still old-fashioned. Someone attracts the authority of the name of the founder of the famous approach, some of the limited goals that can be achieved.
 
 
Of course, everyone would like to have the ability to "read" emotions, like the protagonist of the series "Deceive me." However, we should not forget that emotions are much more complicated and mysterious, and one should not get carried away by frenology and palmistry.
 
 
We talked about the three most common myths about emotions in Affective Computing. It is important to eradicate such misconceptions so that these technologies can work for the benefit of humanity with precision and impartiality.
 
 
Author : Olga Perepelkina, chief research officer of Neurodata Lab.
 
 
References :
 
 
[1]Harry J. Witchel et al. A trigger-substrate model for smiling during an automated formative quiz, Proceedings of the 36th European Conference on Cognitive Ergonomics - ECCE'18 (2018). DOI: ??? /???r3r3148.  
 
[2]Airline Passenger Profiling Based on Fuzzy Deep Machine Learning (2016). Zheng, Yu-Jun et al. doi: ??? /TNNLS.???r3r3156.