We analyzed the contribution of electroencephalogram (EEG) data, age, sex, and personality traits to emotion recognition processes—through the classification of arousal, valence, and discrete emotions labels—using feature selection techniques and machine learning classifiers. EEG traits and age, sex, and personality traits were retrieved from a well-known dataset—AMIGOS—and two sets of traits were built to analyze the classification performance. We found that age, sex, and personality traits were not significantly associated with the classification of arousal, valence and discrete emotions using machine learning. The added EEG features increased the classification accuracies (compared with the original report), for arousal and valence labels. Classification of arousal and valence labels achieved higher than chance levels; however, they did not exceed 70% accuracy in the different tested scenarios. For discrete emotions, the mean accuracies and the mean area under the curve scores were higher than chance; however, F1 scores were low, implying that several false positives and false negatives were present. This study highlights the performance of EEG traits, age, sex, and personality traits using emotion classifiers. These findings could help to understand the traits relationship in a technological and data level for personalized human-computer interactions systems.
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.
Emotion recognition systems from physiological signals are innovative techniques that allow studying the behavior and reaction of an individual when exposed to information that may evoke emotional reactions through multimedia tools, for example, video games. This type of approach is used to identify the behavior of an individual in different fields, such as medicine, education, psychology, etc., in order to assess the effect that the content has on the individual that is interacting with it. This article shows a systematic review of articles that report studies on emotion recognition with physiological signals and video games, between January 2010 and April 2016. We searched in eight databases, and found 15 articles that met the selection criteria. With this systematic review, we found that the use of video games as emotion stimulation tools has become an innovative field of study, due to their potential to involve stories and multimedia tools that can interact directly with the person in fields like rehabilitation. We detected clear examples where video games and physiological signal measurement became an important approach in rehabilitation processes, for example, in Posttraumatic Stress Disorder (PTSD) treatments. Emotion recognition techniques using physiological signals and video games -Systematic review- ResumenLos sistemas de reconocimiento emocional a partir de señales fisiológicas son técnicas innovadoras que permiten estudiar el comportamiento y la reacción de un individuo cuando está expuesto a información que puede evocar reacciones emotivas por medio de herramientas multimedia como, por ejemplo, los videojuegos. Este tipo de enfoque se utiliza para identificar el comportamiento de un individuo en diferentes campos, entre los que están la medicina, la educación y la psicología, entre otros, para evaluar el efecto que tienen los contenidos con los que interactúa. La revisión sistemática que aquí se expone, de artículos que reportan trabajos de reconocimiento emocional con señales fisiológicas y videojuegos entre enero de 2010 y abril de 2016, se realizó con 15 artículos, hallados en ocho bases de datos, los cuales cumplían con los criterios de selección de la búsqueda. Esta revisión sistemática reveló que el uso de videojuegos como herramientas de estimulación emocional se ha convertido en un campo de estudio innovador, debido a su potencial para involucrar historias y herramientas multimedia que pueden interactuar directamente con la persona en campos como la rehabilitación. Se detectaron ejemplos claros donde los videojuegos y la medición de la señal fisiológica se convierten en un enfoque importante para el proceso de rehabilitación, por ejemplo, en los tratamientos de trastorno por estrés postraumático (TEPT).Palabras clave: Biofeedback; Reconocimiento de emociones; Señales fisiológicas; Videojuegos. ResumoOs sistemas de reconhecimento emocional a partir de sinais fisiológicos são técnicas inovadoras que permitem estudar o comportamento e a reação de um indivíduo quando está exposto a info...
Among brain-computer interface studies, electroencephalography (EEG)-based emotion recognition is receiving attention and some studies have performed regression analyses to recognize small-scale emotional changes; however, effective brain regions in emotion regression analyses have not been identified yet. Accordingly, this study sought to identify neural activities correlating with emotional states in the source space. We employed independent component analysis, followed by a source localization method, to obtain distinct neural activities from EEG signals. After the identification of seven independent component (IC) clusters in a k-means clustering analysis, group-level regression analyses using frequency band power of the ICs were performed based on Russell’s valence–arousal model. As a result, in the regression of the valence level, an IC cluster located in the cuneus predicted both high- and low-valence states and two other IC clusters located in the left precentral gyrus and the precuneus predicted the low-valence state. In the regression of the arousal level, the IC cluster located in the cuneus predicted both high- and low-arousal states and two posterior IC clusters located in the cingulate gyrus and the precuneus predicted the high-arousal state. In this proof-of-concept study, we revealed neural activities correlating with specific emotional states across participants, despite individual differences in emotional processing.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.