A Multidimensional Culturally Adapted Representation of Emotions for Affective Computational Simulation and Recognition

Abstract

One of the main challenges in affective computing is the development of models to represent the information that is inherent to emotions. It is necessary to consider that the terms used by humans to name emotions depend on the culture and language used. This paper presents an experiment-based method to represent and adapt emotion terms to different cultural environments. We propose using circular boxplots to analyze the distribution of emotions in the Pleasure-Arousal space. From the results of this analysis, we define a new cross-cultural representation model of emotions in which each emotion term is assigned to an area in the Pleasure-Arousal space. An emotion is represented by a vector in which the direction indicates the type, and the module indicates the intensity of the emotion. We propose two methods based on fuzzy logic to represent and express emotions: the emotion representation process in which the term associated with the recognized emotion is defuzzified and projected as a vector in the Pleasure-Arousal space; and the emotion expression process in which a fuzzification of the vector is produced, generating a fuzzy emotion term that is adapted to the culture and language in which the emotion will be used.

From Affect Theoretical Foundations to Computational Models of Intelligent Affective Agents

“…Hence, the emotional experience, which is the relation between affect and cognition, varies from individual to individual. Considering this fact, the representation of these features in believable intelligent affective agents becomes essential in order to highlight their singularities [7,73,74]. According to [75], "among the most important features of a believable agent are a marked personality and emotions".…”

A BDI Empathic Agent Model Based on a Multidimensional Cross-Cultural Emotion Representation

“…To translate the four affective categories associated with the dimensions of pleasure and arousal (i.e., pleasure and its opposite misery, and arousal and its opposite "Sleepiness") into the target languages (i.e., Portuguese and Swedish), we followed the methodology presented in [220]. According to this methodology, for the first experiment (concerning identification of suitable pleasure-arousal end-points), a set of labels was chosen for each language.…”

“…By this approach it is necessary to assume that the distribution of affective labels in the pleasure-arousal space is equal and uniform. Although, this way of representing affective labels is artificial and is far from how affective states are distributed throughout the pleasure-arousal space as demonstrated in work presented at [220]. In addition, in a point-based approach, it is complex to assign a level of uncertainty that a random point belongs to a certain label or represent the transitions between two affective states.…”

“…In [220], we present a new cross-cultural model of emotion representation for affective computing. Our model differs from the representations discussed in Section 3.2, by providing a new system for representing affective states based on the use of probability areas to define each affective state in the pleasure-arousal space.…”

“…To do that, we establish -59 -3.4. EXPERIMENT DESIGN two processes based on a fuzzy logic approach: the Emotion Representation Process, which is a defuzzification process, which allows representing words related to affective states in the pleasure-arousal space adapted to the cultural environment; and the Emotion Expression Process, that is a fuzzification process, which determines an emotion label in a specific language from a pair of pleasure and arousal values [220]. These processes allow the agent to express its affective state and represent the perceived affective state using the same interpretation of the fuzzy emotional terms used by its human interlocutor and adapted to his/her cultural environment.…”