Responsive Emotional Processing System
Everything can be represented with data. All the arts, sciences, and emotion. Everything. It can all rendered in ones and zeros.
Responsive Emotional Processing System (REPS) harnesses the power of machine learning to optimize core datasets of human problem solving driven by emotion and reason. The responsive machine learning system utilizes deep learning to lift our relevant data on emotions, obstacles, solutions, and actions.
The capacity of deep learning to understand human reason and emotion through data will clarify many aspects of human behavior. Neural networks quantifying feelings, intentions, motives and expectations around solving a perceived obstacle is the cornerstone of the system. Let’s break down the basics on big data.
1. Determine Emotional Direction
Meet the 4 most powerful forces in life. All human behavior is navigated by the energetic dance these 4 core emotions orchestrate. Joy is the opposite of sadness and fear is the opposite of anger. These are the only 4 reasons anyone has ever gone to jail, picked up a gun, or set sail for the unknown. Structuring and filtering all forms of emotional expression in this manner reduces the partition between human and AI emotional intelligence. Emotional complexity is trained by numerically ranking the intensity of each core emotion associated with any event or thought. The data driven emotional architecture is called the 4 Core Emotion System (4CES). The system integrates cognitive, physiological, and behavioral aspects of emotion.
4CES filters all types of emotional expression to our 4 core datasets of emotion, which are globally accepted as general states of being.
The model enables the sorting of all forms of human expression of emotion, including our emotional lexicon, to just four emotions, and eliminates most nuisances of literature, language and culture. It simply integrates our emotional world into the virtual world with clean, well structured, emotional datasets focused on our emotional interpretation of the energy in motion within our bodies. The integration of 4CES into REPS empowers a truly emotional understanding of human intuition applied to overcoming a problem or obstacle. The validity is self-evident with the below illustration.
The words an individual uses to express an emotion is unique and limited to his or her vocabulary. This has been an obstacle for the field of sentiment analysis. The Responsive Emotional Processing System integrates 4CES to assign numerical values to the intensity or weight of the sensations and feelings of our emotional expressions. The expression of emotion is truly only subject to the physiology, behavioral and cognitive emotional weight an individual chooses. A response to an event is truly, up to how three emotional components developed from birth. Humans are extremely adaptable. This fact carries over to our emotional world as well. A fearful event for one individual might be a joyful event for the next. The first day of middle school is an example of how emotional expression may differ between children.
Now let us focus on the child who expresses anger towards the new school year. Most sentiment analysis machine learning models focus on identifying positive, negative or neutral aspects of emotion. This type of sentiment analysis model would produce an output of ‘negative’ for the child expressing a degree of anger. It lacks a deeper understanding of the cognitive, physiological, and behavioral aspects of emotion. A ‘negative’ sentiment could as easily been caused by fear or sadness. The 4 Core Emotion System empowers a much more nuanced understanding of our emotional world by applying a machine learning model trained in the emotional expressions associated with each core emotion. All expressions of emotion will then in some degree be found on the emotional compass with the cardinal directions equal to the 4 core emotions. The model recognizes the child has “frustrated” expressions of emotion as a form of the core emotion of anger with an emotional weight of 5. The below illustrates how an emotion expressed may be defined by the intensity or weight of the feeling or sensation associated by the core emotion.
The weight of the illustrated sub-emotion gets heavier as the numerical value of each card in a suite increases. This demonstrates how the core emotions of Joy, Fear, Sadness and Anger may vary in weight or feeling and be triggered by various sub-emotions.
Multiple core emotions may express at the same time. For example, an individual may have simultaneous expressions of fear and joy on an inaugural skydiving expedition. Correlating expressions of emotion with an event like skydiving seems straightforward, but the debate regarding the physiological, behavioral and cognitive components of emotion is highly contested from the leaders in the field. Neuroscientists to psychologists only have theories on the interplay of distinguishable core emotional energy in motion within our bodies. 4CES attempts to categorize and filter emotion in way that stays in line with the cutting-edge research. Coinciding expressions of joy and sadness are not compatible with the 4CES. In addition, fear and anger may not simultaneously be expressed. The event or obstacle triggering the emotions may only contain two cardinal directions at the same time and must be adjacent to one another. The Responsive Emotional Processing System (REPS) analyzes the following forms of emotional expression.
- Vocal – Emotion is revealed in vocal intonations. The physical biological components include lungs, vocal folds, and the articulators.
- Body Language – Analysis of emotional expression centered around how we use our muscles to communicate is crucial to unlocking emotional intelligence. This includes gestures, eye movement, touch and use of space.
- Physiological – Internal biological reactions to an event or thought triggered by an emotion may quantified with sensors.
- Artistic – Emotion is expressed and perceived in photography, paintings, literature, dance, music, theater, cinema, sculpture, picture form, and architecture.
- Social Communication – Emotional expression through social communication may be analyzed at an individual level or data set.
Let’s move to the second step of the Responsive Emotional Processing System (REPS).
2. Define the Obstacle
The Responsive Emotional Processing System defines an obstacle as a thing that blocks one’s way, prevents, or hinders progress towards optimizing a joyful state of being.
Many of the obstacles in our lives are sorted, filtered and categorized for our convenience. Companies like Amazon, Facebook and Google have a tremendous amount on quality data on the best solutions to overcome a problem. APIs and other software allow third parties to access this big data to sort, filter and categorize in a unique and meaningful manner, allowing us to target a problem from multiple datasets.
Most obstacles we face in our daily lives have multiple attributes or features. Being reflective and asking the right questions is crucial for creating the proper datasets. For example, an individual is trying to find the fastest way to the beach. Some features of this obstacle would include routes, traffic, accidents, time, day, holidays and weather. The features help create a dataset for the particular obstacle, illustrating how each obstacle will have its own dataset of features and labels for deep learning. The datasets are unique down to the quantified core emotional expressions of the individual solving the obstacle. The integration of 4CES to the expressions of emotion around driving to the beach enhances and empowers AI’s ability lift the obstacle or problem with emotional intelligence. Our perceptions of this emotional intelligence will blur the lines between human and artificial intuitiveness.
3. Quantify the Solutions
The Responsive Emotional Processing System defines a solution as a means of solving a problem or dealing with an obstacle weighing on these emotions.
The Responsive Emotional Processing System (REPS) sorts and categorizes solution data on any product, service or idea to 4 core datasets. These datasets are Reliability, Ease of Use, Price and Safety.
Core Datasets of a Solution
Multichannel sentiment analysis has shown rating a solution by these datasets unlocks both emotional and rational aspects of human decision-making processes. What if our 4 core evaluations of a solution are all that is necessary to guide AI through the emotional decision making process? These four core datasets are the foundation of our decision making process. Data on these attributes are readily available through multiple channels. Product reviews, surveys, comments, news articles, post, review websites and buying habits will offer guidance for the structuring of this data.
Structuring the Unstructured Data
The classes and features for each core dataset modifies to each problem or obstacle the solution solves. Price may represent a social or economic cost based on the solution. REPS goes over all the options, collaborative and content based, and recommends the solution an individual likes best with consideration of relevant emotional parameters around these 4 core attributes. The 4 core datasets of a solution are used to train the neural network once transformed into vectors. Massive amounts of training data is required for the neural network, allowing for more training iterations, weight updates, and a better-tuned productive neural network when production starts.
The quality of being trustworthy or performing consistently well.
Product – You choose Apple products on the perceived longevity.
Service – You shop Amazon for the benefits that other retailers can’t match.
Idea – You discovered limiting dairy and carbs as the maintainable way to lose weight.
Absence of difficulty or effort
Product – You chose cordless headphones for cleaning the house.
Service – You choose to valet park to avoid looking for a downtown parking spot.
Idea – You grab duct tape from the garage to fix a broken toy.
The amount of money required or the social cost of the action.
Product – You choose to avoid Apple products because of the price point.
Service – You have the carpets cleaned only after receiving a coupon.
Idea – You reported a bullying incident to the school administration.
The condition of being protected from or unlikely to cause danger, risk or injury.
Product – You buy security system after a home invasion.
Service – You have an irregular looking mole removed.
Idea – You only run in the neighborhood with mace and during daylight hours.
As demonstrated, AI will understand a great deal about our emotions by analyzing how we choose the best product, service or idea to overcome an obstacle. Sentiment analysis of big data filtered by our 4 core evaluations to advance emotion AI is a noble journey. Done correctly, AI’s emotional appraisal of a solution will mirror our own solutions in a way that lifts emotion for man and machine.
4. Quantify the Actions
The Responsive Emotional Processing System defines an action as the physical process applied to the solution to solve a problem or obstacle weighing on the emotions.
It’s time for an individual to take action once a solution to an obstacle has been chosen. The difficulty is in how to structure action data so a machine learning model may provide us with valuable emotional insights. The Responsive Emotional Processing System (REPS) filters all types of relevant action data to 4 uniquely identifiable core datasets. These datasets are Reliability, Effort, Progress and Strategy. The datasets have innate emotional value, which nicely complements the 4 core datasets of the solution. The blending of rational and emotional data into a machine learning model opens a pathway to understand human intuition. This intuition will enhance our day to day communication with the machines we use daily.
Core Datasets of an Action
The below diagram illustrates how the filtering process would structure our unstructured action data. Data collected on our actions through self-evaluation or observing filter down to Reliability, Effort, Progress and Strategy. The Responsive Emotional Processing System transforms these core datasets into vectors to train the neural network. The training data is applied to the neural network, allowing for more training iterations, weight updates, and leading to a tuned productive neural network.
Structuring the Unstructured Data
Reliability – The perceived dependability of your actions to achieve a solution
Effort – The desire to apply your actions to a solution
Progress – The onward movement of your actions towards a solution
Strategy – The plan of applying your actions to a solution