A Comprehensive Study on Machine Learning Approaches for Emotion Recognition

Abstract

Emotion recognition is the process to study about the emotions in a human being. This is a research field where one can understand and recognize the feelings of human and ability of expression which varies from each other at great extent. Several methods have been developed to study emotions such as facial expression, speech method, textual method and EEG signal. In this study work, we have reviewed several methods to find an efficiency of emotions up to accurate observations. Several papers on emotion recognition from the year 2007 to 2021 are been explored in this paper to observe the accuracy 95.20% using electroencephalogram (EEG) signal and 95% using EEG signals with statistical features and neural network. The average accuracy ranges in between 63% to 73% using EEG signal and facial expressions, both.