Integrating Emotion Recognition Tools for Developing Emotionally Intelligent Agents

Abstract

Emotionally responsive agents that can simulate emotional intelligence increase the acceptance of users towardsthem, as the feeling of empathy reduces negative perceptual feedback. This has fostered research on emotionalintelligence during last decades, and nowadays numerous cloud and local tools for automatic emotionalrecognition are available, even for inexperienced users. These tools however usually focus on the recognitionof discrete emotions sensed from one communication channel, even though multimodal approaches have beenshown to have advantages over unimodal approaches. Therefore, the objective of this paper is to show ourapproach for multimodal emotion recognition using Kalman filters for the fusion of available discrete emotionrecognition tools. The proposed system has been modularly developed based on an evolutionary approach soto be integrated in our digital ecosystems, and new emotional recognition sources can be easily integrated.Obtained results show improvements over unimodal tools when recognizing naturally displayed emotions