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.


University of Notre Dame

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

1)	Basic emotions theories

2)	Multi-dimension space theories


Main Emotion Theories used by Computational Emotion Models

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

Speech and Language Processing (3rd ed. draft) 

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.

Learn Before

Related