Emotion Classification Research Articles

Emotion Recognition Using EEG Signals and Audiovisual Features with Contrastive Learning.

Multimodal emotion recognition has emerged as a promising approach to capture the complex nature of human emotions by integrating information from various sources such as physiological signals, visual behavioral cues, and audio-visual content. However, current methods often struggle with effectively processing redundant or conflicting information across modalities and may overlook implicit inter-modal correlations. To address these challenges, this paper presents a novel multimodal emotion recognition framework which integrates audio-visual features with viewers' EEG data to enhance emotion classification accuracy. The proposed approach employs modality-specific encoders to extract spatiotemporal features, which are then aligned through contrastive learning to capture inter-modal relationships. Additionally, cross-modal attention mechanisms are incorporated for effective feature fusion across modalities. The framework, comprising pre-training, fine-tuning, and testing phases, is evaluated on multiple datasets of emotional responses. The experimental results demonstrate that the proposed multimodal approach, which combines audio-visual features with EEG data, is highly effective in recognizing emotions, highlighting its potential for advancing emotion recognition systems.

Translation Method of Emotional Expression in Daniel Keyes’ The Minds of Billy Milligan

This study examines the English to Indonesian translation of emotional expressions depicted in Daniel Keyes’s novel “The Minds of Billy Milligan” and its Indonesian translation “24 Wajah Billy.” The primary objectives are to describe the emotional expressions portrayed by the main character and to analyze the methods applied in translating these emotional expressions from English to Indonesian. Employing David Krech’s emotional classification theory and drawing on Vinay and Darbelnet’s translation methods, this qualitative descriptive research identifies 28 emotional classification data in the novel. Eight types of emotion classifications were identified, including 13 instances of fear, 6 instances of anger, 3 instances of hate, 2 instances of happiness, 1 instance of pain, 1 instance of guilt and regret, 1 instance of pride and shame, and 1 instance of love. The translation applies six translation methods used in 39 instances borrowing, literal, transposition, modulation, equivalent, and adaptation. Each emotion is translated using different translation methods. The application of these six methods is divided into three variants: single with 18 instances, couplet with 9 instances, and triplet with 1 instance. The literal method is the most frequently used in translating emotional expression. The translation method aims to preserve the essence of the narrative from the source language to the target language.

CIRG-SL: Commonsense Inductive Relation Graph framework with Soft Labels for Empathetic Response Generation

Empathy, the ability to understand and respond to others’ emotions, is critical in dialogue systems, particularly for applications such as psychological counselling and casual conversation. However, existing approaches often struggle to accurately capture emotional transitions in user utterances and dialogue contexts across multiple levels of granularity. Additionally, the orthogonality of one-hot emotion representations overlooks the subtle relationships between emotion categories. To overcome these limitations, we propose a novel framework: the commonsense inductive relation graph with fine emotional soft labels for empathetic response generation. This framework refines the representation of user utterances by incorporating commonsense knowledge to derive external emotional cues, which are integrated into an adaptive inductive relation graph. This graph explicitly captures and models dynamic emotional trajectories throughout the dialogue. Additionally, we propose a fine-grained soft label construction method that more accurately reflects the nuanced distribution of emotions, replacing the rigid one-hot encoding with a continuous representation that better captures inter-emotion relationships. Our approach achieves strong performance on the benchmark EmpatheticDialogues dataset, with a perplexity score of 27.85, Dist-1 of 1.81, Dist-2 of 6.58, and a dialogue emotion accuracy of 55.65%. These results highlight the effectiveness of our framework in capturing subtle emotions and generating contextually rich, empathetic responses.

An Emotional Dialogue System Using Conditional Generative Adversarial Networks with a Sequence-to-Sequence Transformer Encoder

Understanding the expression of emotion and generating appropriate responses are key steps toward constructing emotional, conversational agents. In this paper, we propose a framework for single-turn emotional conversation generation, and there are three main components in our model, namely, a sequence-to-sequence model with stacked encoders, a conditional variational autoencoder, and conditional generative adversarial networks. For the sequence-to-sequence model with stacked encoders, we designed a two-layer encoder by combining Transformer with gated recurrent units-based neural networks. Because of the flexibility of the sequence-to-sequence model, we adopted a conditional variational autoencoder in our framework, which uses latent variables to learn a distribution over potential responses and generates diverse responses. Furthermore, we regard a conditional variational autoencoder-based, sequence-to-sequence model as the generative model, and the training of the generative model is assisted by both a content discriminator and an emotion classifier, which assists our model in promoting content information and emotion expression. We use automated evaluation and human evaluation to evaluate our model and baselines on the NTCIR short text conversation task (STC-3) Chinese emotional conversation generation (CECG) Subtask dataset [44], and the experimental results demonstrate that our proposed framework can generate semantically reasonable and emotionally appropriate responses.

Is visual information use during facial emotion recognition related to eating disorder symptoms in college-aged men and women? An experimental study

BackgroundPrevious studies of emotion recognition abilities of people with eating disorders used accuracy to identify performance deficits for these individuals. The current study examined eating disorder symptom severity as a function of emotion categorization abilities, using a visual cognition paradigm that offers insights into how emotional faces may be categorized, as opposed to just how well these faces are categorized.MethodsUndergraduate students (N = 87, 50 women, 34 men, 3 non-binary) completed the Bubbles task and a standard emotion categorization task, as well as a set of questionnaires assessing their eating disorder symptomology and comorbid disorders. We examined the relationship between visual information use (assessed via Bubbles) and eating disorder symptomology (EDDS) while controlling for anxiety (STAI), depression (BDI-II), alexithymia (TAS), and emotion regulation difficulties (DERS-sf).ResultsOverall visual information use (i.e. how well participants used facial features important for accurate emotion categorization) was not significantly related to eating disorder symptoms, despite producing interpretable patterns for each emotion category. Emotion categorization accuracy was also not related to eating disorder symptoms.ConclusionsResults from this study must be interpreted with caution, given the non-clinical sample. Future research may benefit from comparing visual information use in patients with an eating disorder and healthy controls, as well as employing designs focused on specific emotion categories, such as anger.

Neural Representations of Emotions in Visual, Auditory, and Modality-Independent Regions Reflect Idiosyncratic Conceptual Knowledge.

Growing evidence suggests that conceptual knowledge influences emotion perception, yet the neural mechanisms underlying this effect are not fully understood. Recent studies have shown that brain representations of facial emotion categories in visual-perceptual areas are predicted by conceptual knowledge, but it remains to be seen if auditory regions are similarly affected. Moreover, it is not fully clear whether these conceptual influences operate at a modality-independent level. To address these questions, we conducted a functional magnetic resonance imaging study presenting participants with both facial and vocal emotional stimuli. This dual-modality approach allowed us to investigate effects on both modality-specific and modality-independent brain regions. Using univariate and representational similarity analyses, we found that brain representations in both visual (middle and lateral occipital cortices) and auditory (superior temporal gyrus) regions were predicted by conceptual understanding of emotions for faces and voices, respectively. Additionally, we discovered that conceptual knowledge also influenced supra-modal representations in the superior temporal sulcus. Dynamic causal modeling revealed a brain network showing both bottom-up and top-down flows, suggesting a complex interplay of modality-specific and modality-independent regions in emotional processing. These findings collectively indicate that the neural representations of emotions in both sensory-perceptual and modality-independent regions are likely shaped by each individual's conceptual knowledge.

MAS-DGAT-Net: A dynamic graph attention network with multibranch feature extraction and staged fusion for EEG emotion recognition

In recent years, with the rise of deep learning technologies, EEG-based emotion recognition has garnered significant attention. However, most existing methods tend to focus on the spatiotemporal information of EEG signals while overlooking the potential topological information of brain regions. To address this issue, this paper proposes a dynamic graph attention network with multi-branch feature extraction and staged fusion (MAS-DGAT-Net), which integrates graph convolutional neural networks (GCN) for EEG emotion recognition. Specifically, the differential entropy (DE) features of EEG signals are first reconstructed into a correlation matrix using the Spearman correlation coefficient. Then, the brain-region connectivity-feature extraction (BCFE) module is employed to capture the brain connectivity features associated with emotional activation states. Meanwhile, this paper introduces a dual-branch cross-fusion feature extraction (CFFE) module, which consists of an attention-based cross-fusion feature extraction branch (A-CFFEB) and a cross-fusion feature extraction branch (CFFEB). A-CFFEB efficiently extracts key channel-frequency information from EEG features by using an attention mechanism and then fuses it with the output features from the BCFE. The fused features are subsequently input into the proposed dynamic graph attention module with a broad learning system (DGAT-BLS) to mine the brain connectivity feature information further. Finally, the deep features output by DGAT-BLS and CFFEB are combined for emotion classification. The proposed algorithm has been experimentally validated on SEED, SEED-IV, and DEAP datasets in subject-dependent and subject-independent settings, with the results confirming the model's effectiveness. The source code is publicly available at: https://github.com/cvmdsp/MAS-DGAT-Net

Comprehensive Analysis of Hybrid Machine Learning Models using Optimization Techniques for Improving Twitter Sentiment

Sentiment analysis (SA), an important part of natural language processing, is a key part of getting useful information from content generated by users, especially on social media sites like Twitter. This paper considers different techniques for analysing and improving sentiments, with a focus on the hybrid SVM_CNN model used with Twitter datasets. Support Vector Machines (SVMs) are used for classification, and Convolutional Neural Networks (CNNs) are used for feature extraction. The SVM_CNN model is proved to be an effective framework for emotion classification tasks. The study looks into different optimization methods, such as GridSearchCV, Genetic Algorithm, Particle Swarm Optimization (PSO), and Bayesian Optimization, to make the SVM_CNN model more accurate and reliable. The success of each optimization method is assessed by how successfully it determines the optimal hyper parameters that are specific to Twitter text data. The results show that Differential Evolution is the most accurate method, over other existing ones. This study helps to improve methods for sentiment analysis by showing how machine learning techniques and advanced optimization algorithms can work together to make them more useful.

Introducing a novel dataset for facial emotion recognition and demonstrating significant enhancements in deep learning performance through pre-processing techniques

Facial expression recognition (FER) plays a pivotal role in various applications, ranging from human-computer interaction to psychoanalysis. To improve the accuracy of facial emotion recognition (FER) models, this study focuses on enhancing and augmenting FER datasets. It comprehensively analyzes the Facial Emotion Recognition dataset (FER13) to identify defects and correct misclassifications. The FER13 dataset represents a crucial resource for researchers developing Deep Learning (DL) models aimed at recognizing emotions based on facial features. Subsequently, this article develops a new facial dataset by expanding upon the original FER13 dataset. Similar to the FER + dataset, the expanded dataset incorporates a wider range of emotions while maintaining data accuracy. To further improve the dataset, it will be integrated with the extended Cohn-Kanade (CK+) dataset.This paper investigates the application of modern DL models to enhance emotion recognition in human faces. By training a new dataset, the study demonstrates significant performance gains compared with its counterparts. Furthermore, the article examines recent advances in FER technology and identifies critical requirements for DL models to overcome the inherent challenges of this task effectively. The study explores several DL architectures for emotion recognition in facial image datasets, with a particular focus on convolutional neural networks (CNNs). Our findings indicate that complex architecture, such as EfficientNetB7, outperforms other DL architectures, achieving a test accuracy of 78.9 %. Notably, the model surpassed the EfficientNet-XGBoost model, especially when used with the new dataset. Our approach leverages EfficientNetB7 as a backbone to build a model capable of efficiently recognizing emotions from facial images. Our proposed model, EfficientNetB7-CNN, achieved a peak accuracy of 81 % on the test set despite facing challenges such as GPU memory limitations. This demonstrates the model's robustness in handling complex facial expressions. Furthermore, to enhance feature extraction and attention mechanisms, we propose a new hybrid model, CBAM-4CNN, which integrates the convolutional block attention module (CBAM) with a custom 4-layer CNN architecture. The results showed that the CBAM-4CNN model outperformed existing models, achieving higher accuracy, precision, and recall metrics across multiple emotion classes. The results highlight the critical role of comprehensive and diverse data in enhancing model performance for facial emotion recognition.

"Hot" affect-related aspects in emotional information processing: The role of facial muscle responses in the direct and indirect processing of emotion categories.

The present study investigated the involvement of facial muscle responses in the indirect and direct processing of emotional facial expressions. Five discrete emotion categories were used, and we assessed both facial muscle and behavioral responses on a trial-by-trial basis. Experiment 1 tested facial muscle activation of clearly visible stimuli in an emotion categorization task. We observed emotion-specific facial muscle responses and corresponding behavioral categorization effects, providing evidence for the specificity of facial muscle activation. By contrast, under masked indirect presentation conditions in which emotional facial expressions were presented as primes in an emotion misattribution procedure, a specific pattern of emotion-congruent and cross-category behavioral misattributions was observed (in line with Rohr et al., 2015, 2018). Multilevel analyses in Study 2 suggest that an emotional reaction feeds into the behavioral decision, as indicated by differential activation of the frontalis lateralis in response to angry faces. Thus, the present study provides evidence that facial muscle responses contribute to behavioral decisions under masked indirect processing conditions. The different pattern of effects in both studies suggests that facial muscle responses index different processes, depending on the processing conditions: sensorimotor simulation in direct processing conditions and emotional reactions in masked indirect processing conditions. We discuss the implications for models that aim to account for facial muscle activity in response to emotional facial expressions. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Personalized Mood-Centric Book Recommendation Integrating Machine Learning with Content Based Filtering

This paper introduces a novel personalized book recommendation system aimed at enhancing subjective well-being (SWB). Despite the vast array of books available on the internet, people often struggle to find literature that aligns with their current emotional state. The system dynamically detects users' emotional states and recommends books tailored to their mood. It utilizes a content-based filtering algorithm to suggest top-rated books in real-time based on the user's current emotional state. For users with low mood, uplifting and inspirational books are recommended, while a mix of happy and sad books is suggested for happy users to acknowledge the nuanced interplay of emotions. Neutral-themed books are proposed to users with a neutral mood for balance. The system employs an emotion classification algorithm for accurate mood detection, analyzing book summaries to extract emotional tones. Users' emotional states are evaluated using a Likert scale, adjusting recommendations accordingly. The methodology involves data collection, preprocessing, emotion classification, and mood meter operation. Results demonstrate the system's effectiveness in providing tailored book recommendations, enriching users' reading experiences.

Sentiment Analysis and Facial Expression Recognition in Customer Service Interactions

In the evolving landscape of digital customer service, the need for advanced methods to accurately understand and respond to customer emotions has become critical. Traditional systems often rely solely on textual data, missing non-verbal cues that significantly contribute to the customer's emotional state. This study proposes a combined approach integrating Facial Expression Recognition (FER) and Natural Language Processing (NLP) to enhance emotion detection accuracy in customer service interactions. The FER component employs Convolutional Neural Networks (CNNs) to analyze facial expressions, while the NLP component uses Long Short-Term Memory (LSTM) networks to process textual data. This multimodal system aims to provide a comprehensive understanding of customer emotions by capturing both verbal and non-verbal cues. Experiments demonstrate that the integrated FER and NLP model significantly outperforms standalone models, achieving an accuracy of 92.3%, compared to 85.2% for FER-only and 87.4% for NLP-only models. The results highlight the benefits of a multimodal approach, showing substantial improvements in both training and validation performance. This study also compares the proposed model with other state-of-the-art models such as the Deep Learning Assisted Semantic Text Analysis (DLSTA) and Multimodal Emotion Recognition using Deep Belief Networks (DBN). While DLSTA achieves higher accuracy in text-based emotion detection, and DBNs provide robust emotion classification by integrating various modalities, our model effectively balances the strengths of both visual and textual data. The findings suggest that integrating FER and NLP can significantly enhance the quality of customer service by enabling more empathetic and effective interactions. Future work will focus on optimizing computational efficiency, addressing data variability, and ensuring adaptability across diverse customer service scenarios.

Hcnnxgboost: A Hybrid Cnn-Xgboost Approach for Effective Emotion Detection in Textual Data

in recent years, emotional analysis has become a key focus in computational studies, driven by the need to understand societal sentiments. this exploration is motivated by its many promising applications, such as community well-being evaluation, human-computer interaction, suicide prevention, and personalized recommendations. even with progress in other areas like identifying expressions from facial cues and speech, the study of text-based emotion recognition remains a fascinating field of research because machines struggle to interpret context, especially compared to human capabilities. our research addresses this by introducing a multiclass text-based emotion detection system that combines a cnn architecture with xgboost for improved classification in natural language processing. we pre-process publicly available datasets and use glove pre-trained word embeddings for better text representation. a major contribution of our work is enhancing the feature space by combining cnn probabilities with the original text data. the proposed hcnnxgboost model outperforms all other machine learning and deep learning algorithms across the emoint, isear, and crowdflower datasets, achieving f-scores of 90.1%, 87.4%, and 62.2%, respectively. experimental evaluations on benchmark datasets show better f-scores, confirming the effectiveness of our approach. comparisons with other classifiers highlight the enhanced performance and effectiveness of our hybrid cnnxgboost (hcnnxgboost) model, making it one of the best solutions for emotion classification in natural language processing tasks.

Towards Emotionally Intelligent Virtual Environments: Classifying Emotions through a Biosignal-Based Approach

This paper introduces a novel method for emotion classification within virtual reality (VR) environments, which integrates biosignal processing with advanced machine learning techniques. It focuses on the processing and analysis of electrocardiography (ECG) and galvanic skin response (GSR) signals, which are established indicators of emotional states. To develop a predictive model for emotion classification, we extracted key features, i.e., heart rate variability (HRV), morphological characteristics, and Hjorth parameters. We refined the dataset using a feature selection process based on statistical techniques to optimize it for machine learning applications. The model achieved an accuracy of 97.78% in classifying emotional states, demonstrating that by accurately identifying and responding to user emotions in real time, VR systems can become more immersive, personalized, and emotionally resonant. Ultimately, the potential applications of this method are extensive, spanning various fields. Emotion recognition in education would allow further implementation of adapted learning environments through responding to the current emotional states of students, thereby fostering improved engagement and learning outcomes. The capability for emotion recognition could be used by virtual systems in psychotherapy to provide more personalized and effective therapy through dynamic adjustments of the therapeutic content. Similarly, in the entertainment domain, this approach could be extended to provide the user with a choice regarding emotional preferences for experiences. These applications highlight the revolutionary potential of emotion recognition technology in improving the human-centric nature of digital experiences.

Evaluation of emotion classification schemes in social media text: an annotation-based approach

BackgroundEmotion analysis of social media texts is an innovative method for gaining insight into the mental state of the public and understanding social phenomena. However, emotion is a complex psychological phenomenon, and there are various emotion classification schemes. Which one is suitable for textual emotion analysis?MethodsWe proposed a framework for evaluating emotion classification schemes based on manual annotation experiments. Considering both the quality and efficiency of emotion analysis, we identified five criteria, which are solidity, coverage, agreement, compactness, and distinction. Qualitative and quantitative factors were synthesized using the AHP, where quantitative metrics were derived from annotation experiments. Applying this framework, 2848 Sina Weibo posts related to public events were used to evaluate the five emotion schemes: SemEval’s four emotions, Ekman’s six basic emotions, ancient China’s Seven Emotions, Plutchik’s eight primary emotions, and GoEmotions’ 27 emotions.ResultsThe AHP evaluation result shows that Ekman’s scheme had the highest score. The multi-dimensional scaling (MDS) analysis shows that Ekman, Plutchik, and the Seven Emotions are relatively similar. We analyzed Ekman’s six basic emotions in relation to the emotion categories of the other schemes. The correspondence analysis shows that the Seven Emotions’ joy aligns with Ekman’s happiness, love demonstrates a significant correlation with happiness, but desire is not significantly correlated with any emotion. Compared to Ekman, Plutchik has two more positive emotions: trust and anticipation. Trust is somewhat associated with happiness, but anticipation is weakly associated with happiness. Each emotion of Ekman’s corresponds to several similar emotions in GoEmotions. However, some emotions in GoEmotions are not clearly related to Ekman’s, such as approval, love, pride, amusement, etc.ConclusionEkman’s scheme performs best under the evaluation framework. However, it lacks sufficient positive emotion categories for the corpus.

Latent profile analysis of transdiagnostic emotional distress, suicidality, and resilience in first responders

BackgroundFirst responders (i.e., law enforcement officers, firefighters, and emergency medical technicians/paramedics), experience significantly higher occupational trauma exposure than U.S. adult workers outside these fields, leading to increased risks of comorbid mental health disorders. Repeated and intense trauma exposure may combine with personal factors to place them at higher risk for suicide. Conversely, first responders may show higher levels of psychological resilience in the face of occupational trauma experiences. Some research exists on resilience, though little is known about suicide resilience in first responder populations. MethodsWe used latent profile analysis (LPA) on a treatment-seeking sample of first responders (N = 340) with measures of posttraumatic stress disorder (PTSD), generalized anxiety, depression, suicidality, and resilience. ResultsWe determined the best fit was a five-class solution, including the following emotional distress categories: minimal (19 %), mild (33 %), moderate (8 %), moderately severe (27 %), and severe (13 %) emotional distress. In this study, all multivariate analyses of variance (MANOVAs) were statistically significant and had large effect sizes ranging from the lowest (resilience) to the largest (depression). LimitationsWe used self-report assessments and not a clinical interview. Also, we did not have data on measures of substance use, emotional dysregulation (e.g., attachment), or trauma exposure. ConclusionsThis study underscores the critical need for developing and implementing transdiagnostic interventions that not only address the spectrum of emotional distress and suicidality but also actively enhance resilience among treatment-seeking first responders.

A method of developing ensemble classifiers for recognizing audio data of various nature

The work developed a method of building ensemble classifiers for recognizing audio data of various nature. The method is a tentative date and requires the following steps. In the first step, the input datasets are selected, which are transformed and divided into training and test samples, respectively. RAVDESS datasets are chosen for the task of audio emotion recognition, music genre recognition is performed on the GTZAN dataset. In the second step, the following seven classifiers were created and investigated as elements of ensemble classifiers: K Nearest Neighbors, Support Vector Machine, Random Forest, XGBoost, Multilayer Perceptron, Convolutional Neural Network and Long Short-term Memory. In the process of training elementary classifiers, the corresponding hyperparameters were adjusted using the Grid Search approach. In the third step, elementary classifiers were combined using the stacking ensemble method with such types of aggregation as soft voting, hard voting, soft voting using the GOMPERTZ function. All possible ensemble combinations starting with three elementary classifiers for recognizing audio emotions and music genres were tested. Therefore, the total number of ensembles studied in the work was 297. The research results for the problem of audio emotion classification showed that the accuracy of recognition according to the Accuracy metric of the best ensemble classifier is 8.1% higher than that of the best elementary classifier in its composition, which is based on on MLP, and according to the F1 metric, this indicator is 8% higher. For the task of recognizing music genres, the corresponding indicators are higher by 5.6 % and 5.2 %, respectively.

What Is Faster than Where in Vocal Emotional Perception.

Voices carry a vast amount of information about speakers (e.g., emotional state; spatial location). Neuroimaging studies postulate that spatial ("where") and emotional ("what") cues are processed by partially independent processing streams. Although behavioral evidence reveals interactions between emotion and space, the temporal dynamics of these processes in the brain and its modulation by attention remain unknown. We investigated whether and how spatial and emotional features interact during voice processing as a function of attention focus. Spatialized nonverbal vocalizations differing in valence (neutral, amusement, anger) were presented at different locations around the head, whereas listeners discriminated either the spatial location or emotional quality of the voice. Neural activity was measured with ERPs of the EEG. Affective ratings were collected at the end of the EEG session. Emotional vocalizations elicited decreased N1 but increased P2 and late positive potential amplitudes. Interactions of space and emotion occurred at the salience detection stage: neutral vocalizations presented at right (vs. left) locations elicited increased P2 amplitudes, but no such differences were observed for emotional vocalizations. When task instructions involved emotion categorization, the P2 was increased for vocalizations presented at front (vs. back) locations. Behaviorally, only valence and arousal ratings showed emotion-space interactions. These findings suggest that emotional representations are activated earlier than spatial representations in voice processing. The perceptual prioritization of emotional cues occurred irrespective of task instructions but was not paralleled by an augmented stimulus representation in space. These findings support the differential responding to emotional information by auditory processing pathways.

Crafting for Emotion Appropriateness in Affective Robotics: Examining the Practicality of the OCC Model

Research in affective robotics has been using emotions to improve human-robot interaction. One important aspect has been to design recognizable and believable emotions in robotics. Recent work argued that externally displayed emotions on robots may or may not be appropriate for a given situation. However, the selection of emotions as appropriate/inappropriate is not trivial. We here examine the practicality of an established model to craft for emotion appropriateness based on situations of interaction. To do so, we explored the use of the Ortony, Clore, and Collins (OCC) model, which provides a psychological framework of appraisal in which the characteristics of situations are defined and connected to emotions, to identify emotion categories and create contrasting perceptions of emotion appropriateness. We then mapped these categories to four recognizable emotions on aerial robots and designed two video clips (3min35s each) of respectively appropriate and inappropriate emotions. The clips were evaluated in an online study ( N =100) where significant differences were found in attitudes toward the robot's emotions. This paper contributes initial findings to designing for emotion appropriateness.

Emotion Recognition Using EEG Signals through the Design of a Dry Electrode Based on the Combination of Type 2 Fuzzy Sets and Deep Convolutional Graph Networks.

Emotion is an intricate cognitive state that, when identified, can serve as a crucial component of the brain-computer interface. This study examines the identification of two categories of positive and negative emotions through the development and implementation of a dry electrode electroencephalogram (EEG). To achieve this objective, a dry EEG electrode is created using the silver-copper sintering technique, which is assessed through Scanning Electron Microscope (SEM) and Energy Dispersive X-ray Analysis (EDXA) evaluations. Subsequently, a database is generated utilizing the designated electrode, which is based on the musical stimulus. The collected data are fed into an improved deep network for automatic feature selection/extraction and classification. The deep network architecture is structured by combining type 2 fuzzy sets (FT2) and deep convolutional graph networks. The fabricated electrode demonstrated superior performance, efficiency, and affordability compared to other electrodes (both wet and dry) in this study. Furthermore, the dry EEG electrode was examined in noisy environments and demonstrated robust resistance across a diverse range of Signal-To-Noise ratios (SNRs). Furthermore, the proposed model achieved a classification accuracy of 99% for distinguishing between positive and negative emotions, an improvement of approximately 2% over previous studies. The manufactured dry EEG electrode is very economical and cost-effective in terms of manufacturing costs when compared to recent studies. The proposed deep network, combined with the fabricated dry EEG electrode, can be used in real-time applications for long-term recordings that do not require gel.