Exploring EEG Characteristics to Identify Emotional Reactions under Videogame Scenarios

In this article we present the study of electroencephalography (EEG) traits for emotion recognition process using a videogame as a stimuli tool, and considering two different kind of information related to emotions: arousal-valence self-assesses answers from participants, and game events that repres...

Full description

Saved in:
Bibliographic Details
Published in:Brain sciences 2021-03, Vol.11 (3), p.378
Main Authors: Martínez-Tejada, Laura Alejandra, Puertas-González, Alex, Yoshimura, Natsue, Koike, Yasuharu
Format: Article
Language:English
Subjects:
Algorithms
Arousal
Astronauts
Bands
Classification
Computer & video games
correlation
Design
EEG
EEG signals
Electrodes
Electroencephalography
emotion recognition
Emotions
Entropy
Event-related potentials
human-computer interaction
Machine learning
Physiology
regression
Self evaluation
Statistical analysis
Theta rhythms
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this article we present the study of electroencephalography (EEG) traits for emotion recognition process using a videogame as a stimuli tool, and considering two different kind of information related to emotions: arousal-valence self-assesses answers from participants, and game events that represented positive and negative emotional experiences under the videogame context. We performed a statistical analysis using Spearman's correlation between the EEG traits and the emotional information. We found that EEG traits had strong correlation with arousal and valence scores; also, common EEG traits with strong correlations, belonged to the theta band of the central channels. Then, we implemented a regression algorithm with feature selection to predict arousal and valence scores using EEG traits. We achieved better result for arousal regression, than for valence regression. EEG traits selected for arousal and valence regression belonged to time domain (standard deviation, complexity, mobility, kurtosis, skewness), and frequency domain (power spectral density-PDS, and differential entropy-DE from theta, alpha, beta, gamma, and all EEG frequency spectrum). Addressing game events, we found that EEG traits related with the theta, alpha and beta band had strong correlations. In addition, distinctive event-related potentials where identified in the presence of both types of game events. Finally, we implemented a classification algorithm to discriminate between positive and negative events using EEG traits to identify emotional information. We obtained good classification performance using only two traits related with frequency domain on the theta band and on the full EEG spectrum.
ISSN:2076-3425
2076-3425
DOI:10.3390/brainsci11030378