ABOUT HEARTBEAT

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 a wide range of emotions, the Heartbeat HX platform processes unstructured text that people use to describe their conscious feelings. Our algorithm takes text data and converts it to a binary code representing primary and secondary - “fine-grained” - emotions. The algorithm is unique in its ability to code data at the granular level beyond sentiment.

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.” "Body Sense" is not an emotion, yet it describes a very important part of human experience: 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, knows as "multigrams" in the field of Natural Language Processing (NLP). Each word and phrase represents one or more secondary emotion categories. We use a method called “bag of words" as a base, and power it with NLP rules for recognizing negations, ambiguous words and context.

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.

Many Ways to Analyze Emotions

Measuring Emotions for CX & EE (or anything else)

by Howard Lax, Ph.D. (edited for length with the permission of the author)

To understand what people DO you have to understand what they FEEL.

Our emotions — how we feel — are key to determining how we behave and respond to stimuli. To measure and understand virtually any aspect of consumer (human) behaviour we need to make some effort to measure the emotional dimension.

Measuring emotions involves a classic Catch 22.

Emotions are below the surface in the murky and obscure land of the subconscious. The moment we ask people to rate or assess their feelings and give a “reasoned” answer we move from the realm of subconscious emotions and feelings to the world of thinking. It’s a classic Catch 22.

So where can a marketer/researcher/strategist start?

The following four methods are available for measuring emotions:

 

1: The Traditional Survey Approach — Self Reporting

Essentially, it tells us how we think we feel.

The traditional survey approach is to directly ask respondents to rate or score their feelings on some type of scale. The survey is easy to implement and inexpensive. However, given that we don’t consciously know our feelings, this approach is far from perfect, as it violates the fundamental premise of the separation between thinking and feeling by asking people to think about their feelings. Essentially, it tells us how we think we feel.

 

2: Direct Physical Assessment — Measuring Autonomic Reactions

Direct Assessment is great for small scale tests…

Since feelings elicit physical reactions, why not directly measure neurological and physiological responses such as the heartbeat or brainwaves that can inform us how people are feeling?

This circumvents the need to ask people to think about and articulate their feelings. Direct Assessment is great for small scale tests of how people react to a wide range of stimuli including ideas, concepts, experiences, ads & more, and can be immensely informative.

 

3: Inferential (Implicit) Measurement

IATs can measure respondents’ visceral feelings…

Implicit measurement is useful if you need a representative sample or data at scale. Based on social psychology work regarding bias, Implicit Association Tests (IATs) generally rely upon the speed with which people answer questions about the association between two topics to measure the strength of someone’s feelings.

IATs can measure respondents’ visceral feelings or the strength of their association or attachment to a belief through inferential measurement that is less intrusive than traditional survey questions and more compatible with subconscious measurement.

 

4: Emotion or Empathy Analytics of Unstructured Text

…we can take their comments and analyze their words to determine their underlying emotions…

Unstructured text is a goldmine for exploring feelings. Instead of asking someone to rate or categorize their feelings, we can take their comments and analyze their words to determine their underlying emotions. Does the person express frustration or anger? Are they surprised or delighted?

Analysts used to do this manually,  but now we can automate this function to scale, including using complex algorithms to root out the underlying emotions embedded in what someone has said or written. This is not simple positive/negative sentiment analysis or scoring favorable/negative comments. Rather, it’s developing an algorithm, building a lexicon, curating for a particular category and using Machine Learning tools to unearth the underlying emotions embedded in our language.

This approach can be accomplished in virtually real-time, at scale, and using any unstructured text, from survey open-ends to social media, from call center transcripts to talk-to-chat. So depending on what you want to know, you might not need any new data collection.

Want to know how people feel about any of the estimated six million apps available through Google and Apple Play combined? Just scrape the data and run it through this type of empathy analytics engine.