Speech-oriented negative emotion recognition

ABSTRACTThe large range of potential applications, not only for patients but also for healthy people, that could be achieved by affective BCI (aBCI) makes more latent the necessity of finding a commonly accepted protocol for real-time EEG-based emotion recognition. Based on wavelet package for spectral feature extraction, attending to the nature of the EEG signal, we have specified some of the main parameters needed for the implementation of robust positive and negative emotion classification. 12 seconds has resulted as the most appropriate sliding window size; from that, a set of 20 target frequency-location variables have been proposed as the most relevant features that carry the emotional information. Lastly, QDA and KNN classifiers and population rating criterion for stimuli labeling have been suggested as the most suitable approaches for EEG-base emotion recognition. The proposed model reached a mean accuracy of 98% (s.d. 1.4) and 98.96% (s.d. 1.28) in a subject-dependent approach for QDA and KNN classifier, respectively. This new model represents a step forward towards real-time classification. Although results were not conclusive, new insights regarding subject-independent approximation have been discussed.

Download Full-text

Insensitive Players? A Relationship Between Violent Video Game Exposure and Recognition of Negative Emotions

Frontiers in Psychology ◽

10.3389/fpsyg.2021.651759 ◽

2021 ◽

Vol 12 ◽

Author(s):

Ewa Miedzobrodzka ◽

Jacek Buczny ◽

Elly A. Konijn ◽

Lydia C. Krabbendam

Keyword(s):

Emotion Recognition ◽

Video Game ◽

Negative Emotion ◽

Negative Emotions ◽

Real Life ◽

Lower Sensitivity ◽

Violent Video Game ◽

Causal Direction ◽

Matching Test ◽

The One

An ability to accurately recognize negative emotions in others can initiate pro-social behavior and prevent anti-social actions. Thus, it remains of an interest of scholars studying effects of violent video games. While exposure to such games was linked to slower emotion recognition, the evidence regarding accuracy of emotion recognition among players of violent games is weak and inconsistent. The present research investigated the relationship between violent video game exposure (VVGE) and accuracy of negative emotion recognition. We assessed the level of self-reported VVGE in hours per day and the accuracy of the recognition using the Facial Expressions Matching Test. The results, with adolescents (Study 1; N = 67) and with adults (Study 2; N = 151), showed that VVGE was negatively related to accurate recognition of negative emotion expressions, even if controlled for age, gender, and trait empathy, but no causal direction could be assessed. In line with the violent media desensitization model, our findings suggest that higher self-reported VVGE relates to lower recognition of negative emotional expressions of other people. On the one hand, such lower recognition of negative emotions may underlie inaccurate reactions in real-life social situations. On the other hand, lower sensitivity to social cues may help players to better focus on their performance in a violent game.

Download Full-text

Investigating the Role of Culture on Negative Emotion Expressions in the Wild

Frontiers in Integrative Neuroscience ◽

10.3389/fnint.2021.699667 ◽

2021 ◽

Vol 15 ◽

Author(s):

Emma Hughson ◽

Roya Javadi ◽

James Thompson ◽

Angelica Lim

Keyword(s):

Emotion Recognition ◽

North American ◽

Affective Computing ◽

Negative Emotion ◽

Negative Emotions ◽

Support Vector ◽

Data Sets ◽

Social Signals ◽

Data Set ◽

In The Wild

Even though culture has been found to play some role in negative emotion expression, affective computing research primarily takes on a basic emotion approach when analyzing social signals for automatic emotion recognition technologies. Furthermore, automatic negative emotion recognition systems still train data that originates primarily from North America and contains a majority of Caucasian training samples. As such, the current study aims to address this problem by analyzing what the differences are of the underlying social signals by leveraging machine learning models to classify 3 negative emotions, contempt, anger and disgust (CAD) amongst 3 different cultures: North American, Persian, and Filipino. Using a curated data set compiled from YouTube videos, a support vector machine (SVM) was used to predict negative emotions amongst differing cultures. In addition a one-way ANOVA was used to analyse the differences that exist between each culture group in-terms of level of activation of underlying social signal. Our results not only highlighted the significant differences in the associated social signals that were activated for each culture, but also indicated the specific underlying social signals that differ in our cross-cultural data sets. Furthermore, the automatic classification methods showed North American expressions of CAD to be well-recognized, while Filipino and Persian expressions were recognized at near chance levels.

Download Full-text

Seeing no pain: Assessing the generalizability of racial bias in pain perception

10.31234/osf.io/qj8vw ◽

2020 ◽

Author(s):

Peter Mende-Siedlecki ◽

Jingrun Lin ◽

Sloan Ferron ◽

Christopher Gibbons ◽

Alexis Drain ◽

...

Keyword(s):

Emotion Recognition ◽

Racial Disparities ◽

Pain Perception ◽

Racial Bias ◽

Negative Emotion ◽

Racial Stereotypes ◽

Total N ◽

Black And White ◽

Pain Care ◽

Black Faces

Previous work demonstrates that racial disparities in pain care may stem, in part, from perceptual roots. It remains unresolved, however, whether this perceptual gap is driven by general deficits in intergroup emotion recognition, endorsement of specific racial stereotypes, or an interaction between the two. We conducted four experiments (total N = 635) assessing relationships between biases in pain perception and treatment with biases in the perception of anger, happiness, fear, and sadness. Participants saw Black and White targets making increasingly painful and angry (Experiment 1), happy (Experiment 2), fearful (Experiment 3), or sad expressions (Experiment 4). The effect of target race consistently varied based on the emotion presented. Participants consistently saw pain more readily on White (versus Black) faces. However, while the perception of sadness was also disrupted on Black faces, the perception of anger, fear, and happiness did not vary by target race. Moreover, the tendency to see pain less readily on Black faces predicted similar disruptions in recognizing (particularly negative) expressions, though only racial bias in pain perception facilitated similar biases in treatment. Finally, while endorsement of racial stereotypes about threat facilitated recognition of angry expressions and impeded recognition of happy expressions on Black faces, gaps in pain perception were not reliably related to stereotype endorsement. These data suggest that while racial bias in pain perception is associated with general disruptions in recognizing negative emotion on Black faces, the effects of target race on pain perception are particularly robust and have distinct consequences for gaps in treatment recommendations.

Download Full-text