In this class of theory, there are a limited number of basic and atomic emotions, and all the other emotions are derived from basic emotions. For example, Ekman (1999) proposed that there are six basic emotions, which are surprise, happiness, anger, fear, disgust, and sadness. And Plutchik (1980) proposed that there are eight basic emotions and four pairs: joy–sadness, anger–fear, trust–disgust, and anticipation–surprise.

Basic Emotions Theories

In this class of models, emotions are put into a 2 or 3 dimension space, and the dimensions are valence, arousal, and dominance, where valence is the pleasantness shown by the stimulus, arousal is the intensity of emotions provoked by the stimulus, and dominance the degree of control shown by the stimulus.


Multi-Dimension Space Theories

Computational emotion models in NLP are mostly based on two families of emotion theories:

1)	Basic emotions theories

2)	Multi-dimension space theories


University of Notre Dame

Emotion can be defined as a relatively brief episode of response to the evaluation of an external or internal event. In machine learning, detecting emotions can improve many language processing tasks. For example, an online tutoring system can use emotion detection to see if a student is happy, sad, or bored. And detecting emotions in customer reviews can help businesses improve based on customer feedback.

Emotion in Machine Learning

An on-going but a helpful book resource about NLP
https://web.stanford.edu/~jurafsky/slp3/

Learn Before

Learn After

Learn After