Emotions: Can Machines Understand Them?

Many People Feeling Emotion

The short answer is that they could understand emotions if equipped with the proper sensors and algorithms.

Physiological Components of Emotions
Emotions always have a physiological component. When we feel excited our heart rate changes, skin conductance increases, facial expressions exaggerate. Many physical and physiological signatures of emotional states have been well studied and classified. For example, the facial action coding system developed by Paul Ekman have been used to detect emotion by computer scientists since the 1970s.

Today the advances in photography and affective computing made possible the development of more accurate automated face analysis. This is how it works. 1) The machine “attends” to the facial signals through automated face detection and registration, and “receives” facial signals with high speed cameras. 2) The next step is extracting key signals. In facial expression recognition, the signal components are called Action Units (AU), or the movement changes of individual facial muscles. The machine does this through a variety of algorithms such as principal component analysis, linear discriminant analysis, and support vector machine classifiers. 3) Based on the specific combination of AU, the machine concludes an emotion experienced by the recorded facial expression.

For example, pain is characterized by brow lowering (AU4), orbital tightening (AU6 and 7), eye closure (AU43), nose wrinkling and lip raise (AU9 and 10). After going through the preceding steps and detecting the changes in these Action Units the machine will conclude that the person experiences pain.

Other Key Factors
Physiological changes such as tone of voice, body movements, heart rate and more can be measured with biometric sensors. Many devices already have these sensors and collect the data. The algorithms to analyze this data and make conclusions about emotions are already developed. It’s just a matter of time before machines will actively read our emotions and use this information in ways we hope will benefit us.

The Fit Brains Team

“Brain Training Success”

Can Machines Have Feelings?

Robot with Feeling

Of course not is the intuitive and immediate answer that this question would most likely get. But let’s not be so fast. There is a field in computing called Affective Computing whose goal is to create machines that can detect and interpret human emotions. It uses the appraisal theory of emotions as its guide. This theory is one of the most influential theories of emotions and it is able to bridge the gap between emotions and the symbolic reasoning process favored by the builders of artificial intelligence (AI).

Appraisal Theory

According to the Appraisal Theory, humans determine how they feel about a certain event and entity using a series of template evaluation process. First, we evaluate how novel or familiar something is. Then, we weigh how likely it is to cause a positive or a negative experience in congruence with our goals. Then we evaluate our coping potential: can we influence and control it, can we change it in ways that makes it beneficial to us. Our brains ultimately translate this series of evaluations into a certain feeling towards the event or entity. If it is something familiar, pleasant, reasonably controllable, and congruent with our goals, we are likely to experience positive emotions towards it. If it is something new, unpleasant, out of control, and incongruent with our goals, we are likely to hate it.

So What Does This Mean For Machines?

If the emotional process can be broken down into a series of evaluations with more or less binary outcomes (novel/familiar, controllable/uncontrollable, etc.), then these operations can be performed not just by a human but by a machine too. If we could develop algorithms parallel to the process human brains use to make decisions about familiarity, valence, controllability, and goal congruence, the process through which an emotion is created can be performed by a machine.

Admittedly, we are a long way from the moment when a machine will feel happy or scared, but the Appraisal Theory of emotions provides a roadmap for how we can teach machines to process human emotions.

Stay tuned to learn how machines can learn to detect and interpret human emotions.

Want To Exercise Your Own Emotional & Cognitive Intelligence?

Fit Brains Games

In the meantime, exercise all the areas of your brain with Fit Brains fun and stimulating brain games. Challenge memory, speed of thinking and more today.