Emotion-Aware Explainable Artificial Intelligence for Personality, Emotion, and Mood Simulation

Abstract

This paper is twofold. First, the authors analysed the state of the art on the explainable artificial intelligence (XAI) applied to affective computing, emotion analysis, and sentiment analysis. Second, based on Kaptein’s approach and using the personality, emotion, and mood model proposed by Egges, the authors tested an Emotion-aware XAI framework to determine the affective state of predefined-behaviour autonomous entities in uncertainty contexts. The affective state analysis of eight selected formal use cases was divided into four stages: personality settings, event evaluation, emotions and moods generation, and results classification. Findings suggest that the affective state depends on the type of predominant personality and the influence of the events in the environment.