Cortical Asymmetries and Connectivity Patterns in the Valence Dimension of the Emotional Brain

The Influence of Group Favoritism on Moral Judgment -- Evidence From Event-Related Potential

When judging the morality of an action, individuals may exhibit a bias stemming from group favoritism. It leads to the expression of different moral evaluations of the same behaviors performed by different social groups. The current study used event-related potentials (ERPs) to investigate the influence of in-group favoritism (in-group vs. homogeneous out-group) and out-group favoritism (in-group vs. high-quality out-group) on moral judgments. Two experiments were conducted, showing a higher moral score of the in-group compared to the homogeneous out-group by participants. ERP data indicated that in-group stimulation triggered larger P2 amplitudes than homogeneous out-group. Additionally, a larger N400-like amplitude, localized to the right hemisphere, was observed during the evaluation of the homogeneous out-group. Significantly, when comparing the in-group to the high-quality out-group, there was no discernible difference in moral scores or ERP amplitudes. Overall, the results indicate that in-group favoritism can affect moral judgments, especially when assessing homogeneous out-groups, but it can be reduced by the characteristics of groups.

Variational Phase-Amplitude Coupling Characterizes Signatures of Anterior Cortex Under Emotional Processing

Emotion, an essential aspect in inferring human psychological states, is featured by entangled oscillators operating at multiple frequencies and montages. However, the dynamics of mutual interactions among rhythmic activities in EEGs under various emotional expressions are unclear. To this end, a novel method named variational phase-amplitude coupling is proposed to quantify the rhythmic nesting structure in EEGs under emotional processing. The proposed algorithm lies in variational mode decomposition, featured by its robustness to noise artifacts and its merit in avoiding the mode-mixing problem. This novel method reduces the risk of spurious coupling compared to that with ensemble empirical mode decomposition or iterative filter when evaluated by simulations. An atlas of cross-couplings in EEGs under eight emotional processing is established. Mainly, α activity in the anterior frontal region serves as a critical sign for neutral emotional state, whereas γ amplitude seems to be linked with both positive and negative emotional states. Moreover, for those γ-amplitude-related couplings under neutral emotional state, the frontal lobe is associated with lower phase-given frequencies while the central lobe is attached to higher ones. The γ-amplitude-related coupling in EEGs is a promising biomarker for recognizing mental states. We recommend our method as an effective tool in characterizing the entangled multifrequency rhythms in brain signals for emotion neuromodulation.

Deep Learning Methods for Multi-Channel EEG-Based Emotion Recognition

Currently, Fourier-based, wavelet-based, and Hilbert-based time–frequency techniques have generated considerable interest in classification studies for emotion recognition in human–computer interface investigations. Empirical mode decomposition (EMD), one of the Hilbert-based time–frequency techniques, has been developed as a tool for adaptive signal processing. Additionally, the multi-variate version strongly influences designing the common oscillation structure of a multi-channel signal by utilizing the common instantaneous concepts of frequency and bandwidth. Additionally, electroencephalographic (EEG) signals are strongly preferred for comprehending emotion recognition perspectives in human–machine interactions. This study aims to herald an emotion detection design via EEG signal decomposition using multi-variate empirical mode decomposition (MEMD). For emotion recognition, the SJTU emotion EEG dataset (SEED) is classified using deep learning methods. Convolutional neural networks (AlexNet, DenseNet-201, ResNet-101, and ResNet50) and AutoKeras architectures are selected for image classification. The proposed framework reaches 99% and 100% classification accuracy when transfer learning methods and the AutoKeras method are used, respectively.

From Intricacy to Conciseness: A Progressive Transfer Strategy for EEG-Based Cross-Subject Emotion Recognition

Emotion plays a significant role in human daily activities, and it can be effectively recognized from EEG signals. However, individual variability limits the generalization of emotion classifiers across subjects. Domain adaptation (DA) is a reliable method to solve the issue. Due to the nonstationarity of EEG, the inferior-quality source domain data bring negative transfer in DA procedures. To solve this problem, an auto-augmentation joint distribution adaptation (AA-JDA) method and a burden-lightened and source-preferred JDA (BLSP-JDA) approach are proposed in this paper. The methods are based on a novel transfer idea, learning the specific knowledge of the target domain from the samples that are appropriate for transfer, which reduces the difficulty of transfer between two domains. On multiple emotion databases, our model shows state-of-the-art performance.

Neural Networks with Emotion Associations, Topic Modeling and Supervised Term Weighting for Sentiment Analysis

Automated sentiment analysis is becoming increasingly recognized due to the growing importance of social media and e-commerce platform review websites. Deep neural networks outperform traditional lexicon-based and machine learning methods by effectively exploiting contextual word embeddings to generate dense document representation. However, this representation model is not fully adequate to capture topical semantics and the sentiment polarity of words. To overcome these problems, a novel sentiment analysis model is proposed that utilizes richer document representations of word-emotion associations and topic models, which is the main computational novelty of this study. The sentiment analysis model integrates word embeddings with lexicon-based sentiment and emotion indicators, including negations and emoticons, and to further improve its performance, a topic modeling component is utilized together with a bag-of-words model based on a supervised term weighting scheme. The effectiveness of the proposed model is evaluated using large datasets of Amazon product reviews and hotel reviews. Experimental results prove that the proposed document representation is valid for the sentiment analysis of product and hotel reviews, irrespective of their class imbalance. The results also show that the proposed model improves on existing machine learning methods.