Heartbeat Map of Emotions
About Emotions and Human Brain
We crafted our taxonomy to reflect the most advanced findings in psychology and affective neuroscience. Human emotions and feelings are part of a complex system that is not yet completely understood. They are generated by an interaction of our environment, the body and some older parts of the brain, and governed by our newer and more advanced brain. Billions of synaptic connections fire at the same time creating the wonderful complexity of our inner emotional world.
Basic emotions are driven by evolutionary survival needs that are hard-wired in the limbic system: fear, rage, care, search, panic, play and lust. Secondary emotions, emotional states, and feelings arise in our awareness after they have been processed in the neocortex.
It is increasingly important to understand and measure collective emotions and feelings that heavily influence some of the most vital decisions in history, such as elections. A new study by Cornell University neuroscientist Adam Anderson showed that although feelings are personal and subjective, the human brain turns them into a standard code that objectively represents emotions across different senses, situations and even people.
"We discovered that fine-grained patterns of neural activity within the orbitofrontal cortex, an area of the brain associated with emotional processing, act as a neural code which captures an individual’s subjective feeling. If you and I derive similar pleasure from sipping a fine wine or watching the sun set, our results suggest it is because we share similar fine-grained patterns of activity in the orbitofrontal cortex. Despite how personal our feelings feel, the evidence suggests our brains use a standard code to speak the same emotional language." (Adam Anderson)
One of the world’s leading affective neuroscientists Joseph LeDoux supports these findings and offers his view of how emotions arise in the mind from the deep unconscious primary emotions to conscious feelings that can be expressed, described and shared. In his 2015 paper “Feelings: What Are They & How Does the Brain Make Them?” he introduces the term “conscious feelings”, explains how they are formed, and describes them as valid indications of human emotions.
“Conscious feelings, like the feeling of being afraid or angry or happy or in love or disgusted, are in one sense no different from other states of consciousness, such as the awareness that the roundish, reddish object before you is an apple.” (Joseph LeDoux, Rethinking the Emotional Brain, 2012 Neuron)
Today, we can understand emotions using many implicit objective measurement tools. Yet, language still remains a rich source of data - the only source that can show the wide range of human emotions.
Heartbeat Segmentation of Emotions
To understand and analyze emotions, Heartbeat text analytics processes language (unstructured text) that people use to describe their conscious feelings. The algorithm takes unstructured text data and converts it to binary code representing primary and secondary (or “fine-grained”) emotions.
The algorithm is unique in its ability to code data at the granular level beyond sentiment or primary emotions. Heartbeat differentiates 15 kinds of Anger (ex: Aggression & Violence, Annoyance & Exasperation, Criticism, Impatience, etc.), 16 subcategories of Fear, 20 subcategories of Joy, 10 subcategories of Love, 13 subcategories of Sadness, etc.
Heartbeat emotion segmentation was designed based on a well-known classification of emotions by Dr. W. G. Parrott of Georgetown University. Three primary emotions - Trust, Disgust, and Void (i.e. explicit lack of emotion) - have been added to Parrott’s Classification (Joy, Love, Anger, Fear, Sadness, and Surprise), along with “Body Sense”, which is not necessarily an emotion, but has been included to describe feelings that are related to senses (ex: cold, tasty, smelly, etc.).
Heartbeat emotion text analytics is based on a comprehensive taxonomy of over 20,000 emotional words and phrases (multigrams), professionally coded into 100 secondary categories. Each word and phrase represent one or more secondary emotion categories. We use a method called “bag of words" as a base, and power it with Natural Language Processing (NLP) and supervised machine learning to recognize negations and ambiguous words.
The rich taxonomy was built in-house by the Heartbeat team, and not crowd-sourced like other similar taxonomies. Heartbeat taxonomy is the most comprehensive in the world in terms of the number of fine-grained emotions included.