Human Emotional Expressions Research Articles

Chinese Emotional Dialogue Response Generation via Reinforcement Learning

In an open-domain dialogue system, recognition and expression of emotions are the key factors for success. Most of the existing research related to Chinese dialogue systems aims at improving the quality of content but ignores the expression of human emotions. In this article, we propose a Chinese emotional dialogue response generation algorithm based on reinforcement learning that can generate responses not only according to content but also according to emotion. In the proposed method, a multi-emotion classification model is first used to add emotion labels to the corpus of post-response pairs. Then, with the help of reinforcement learning, the reward function is constructed based on two aspects, namely, emotion and content. Among the generated candidates, the system selects the one with long-term success as the best reply. At the same time, to avoid safe responses and diversify dialogue, a diversity beam search algorithm is applied in the decoding process. The comparative experiments demonstrate that the proposed model achieves satisfactory results according to both automatic and human evaluations.

Do Emotional Cues Influence the Performance of Domestic Dogs in an Observational Learning Task?

Using social information is not indiscriminate and being able to choose what to copy and from whom to copy is critical. Dogs are able to learn socially, to recognize, and respond to dog as well as human emotional expressions, and to make reputation-like inferences based on how people behave towards their owner. Yet, the mechanisms dogs use for obtaining and utilizing social information are still to be fully understood, especially concerning whether emotional cues influence dogs’ social learning. Therefore, our main aim was to test the hypothesis that an emotionally charged (negative, positive, or neutral) interaction with the demonstrator of a “V” detour task prior to testing would affect subjects’ performance, by: (i) changing the value of the information provided by the demonstrator or (ii) changing the valence of the learning environment. Our experimental design consisted of three phases: pre-test (subjects were allowed to solve the task alone); emotional display (dogs watched the unfamiliar human behaving in either a positive, negative or neutral way towards their owner); test (demonstrator showed the task and subjects were allowed to move freely). Only dogs that failed in pre-test were considered for analysis (n = 46). We analyzed four dependent variables: success, time to solve the task, latency to reach the fence and matching the side of demonstration. For each, we used four models (GEEs and GLMMs) to investigate the effect of (1) demographic factors; (2) experimental design factors (including emotional group); (3) behavior of the dog; and (4) side chosen and matching. All models took into account all trials (random effect included) and the first trials only. Our findings corroborate previous studies of social learning, but present no evidence to sustain our hypothesis. We discuss the possibility of our stimuli not being salient enough in a task that involves highly motivating food and relies on long and highly distracting interval between phases. Nevertheless, these results represent an important contribution to the study of dog behavior and social cognition and pave the way for further investigations.

Revisiting the Embryology of the Facial Muscles, the Superficial Musculoaponeurotic System, and the Facial Nerve

The facial muscles are responsible for nonverbal expression, and the manner by which these muscles function to express various emotions are reviewed. How one recognizes these various facial expressions and how individuals can alter their facial expression are discussed. The methodology for cataloging facial expressions is also presented. The embryology of the facial muscles; the facial ligaments; and the supporting superficial musculoaponeurotic system, which magnifies the muscle movements, is also reviewed as is the embryology of the facial nerve, which innervates these muscles. Also, a detailed MR imaging atlas of the facial muscles is presented.Learning Objective: The reader will learn how the facial muscles develop and how they are the means of human nonverbal emotional expression. The anatomy of the facial ligaments and the superficial musculoaponeurotic system are also discussed

The Cyborg Philharmonic: Synchronizing interactive musical performances between humans and machines

Music offers a uniquely abstract way for the expression of human emotions and moods, wherein melodic harmony is achieved through a succinct blend of pitch, rhythm, tempo, texture, and other sonic qualities. The emerging field of “Robotic Musicianship” focuses on developing machine intelligence, in terms of algorithms and cognitive models, to capture the underlying principles of musical perception, composition, and performance. The capability of new-generation robots to manifest music in a human-like artistically expressive manner lies at the intersection of engineering, computers, music, and psychology; promising to offer new forms of creativity, sharing, and interpreting musical impulses. This manuscript explores how real-time collaborations between humans and machines might be achieved by the integration of technological and mathematical models from Synchronization and Learning, with precise configuration for the seamless generation of melody in tandem, towards the vision of human–robot symphonic orchestra. To explicitly capture the key ingredients of a good symphony—synchronization and anticipation—this work discusses a possible approach based on the joint strategy of: (i) Mapping— wherein mathematical models for oscillator coupling like Kuramoto could be used for establishing and maintaining synchronization, and (ii) Modelling—employing modern deep learning predictive models like Neural Network architectures to anticipate (or predict) future state changes in the sequence of music generation and pre-empt transitions in the coupled oscillator sequence. It is hoped that this discussion will foster new insights and research for better “real-time synchronized human-computer collaborative interfaces and interactions”.

SYSTEM OF AUTOMATIC DETERMINATION OF TEXT TONE

In the work, the methods of sentiment analysis of the text are considered. The system of emotion detection of Ukrainian-language texts based on dictionaries and rules is proposed. The developed software downloads text information in various formats and carries out tokenization and lemmatization procedures using the Python TokenizeUKand pymorphy2 libraries. As a result, an array of words in the basic grammatical form using for determining the tone of the text is formed. The obtained word base was analyzed using a tonal dictionary of the Ukrainian language. A dictionary of synonyms was used to expand the vocabulary. If there is no word in the tonal dictionary, the tonality value of its nearest synonym is used for further calculations. Computer analysis of textual information was performed in five emotional categories namely: very positive, positive, neutral, negative, and very negative tone of words. To increase the accuracy and validity of sentiment analysis, coefficients were used that take into account the various emotional load of words of different speech parts and their dissimilar impact on the overall assessment of the text tone. The proposed system of sentiment analysis assumes a greater emotional influence of adjectives compared to verbs and nouns. Since the tone of textual information and the expression of human emotions are subjective factors, the means of fuzzy modeling are used for sentiment analysis of texts. This approach makes it possible to take into account the contribution of all emotional categories in the final evaluation of the text. As a result of an aggregation of normalized data on different emotion categories and defuzzification by the method of the center of gravity for one-element sets, a quantitative estimate of the emotional tone of texts was obtained. The developed system of sentiment analysis was tested on Ukrainian-language texts from different sources and different emotional tones. The use of additional tools provides the analysis of more words in the text and the degree of their emotional tone, which leads to more correct detection of the tone of the whole text. Key words : computer text analysis, sentiment analysis, tokenization, tonality dictionary, fuzzy modeling.

Emotion Analysis: Bimodal Fusion of Facial Expressions and EEG

With the rapid development of deep learning and artificial intelligence, affective computing, as a branch field, has attracted increasing research attention. Human emotions are diverse and are directly expressed via non-physiological indicators, such as electroencephalogram (EEG) signals. However, whether emotion-based or EEG-based, these remain single-modes of emotion recognition. Multi-mode fusion emotion recognition can improve accuracy by utilizing feature diversity and correlation. Therefore, three different models have been established: the single-mode-based EEG-long and short-term memory (LSTM) model, the Facial-LSTM model based on facial expressions processing EEG data, and the multi-mode LSTM-convolutional neural network (CNN) model that combines expressions and EEG. Their average classification accuracy was 86.48%, 89.42%, and 93.13%, respectively. Compared with the EEG-LSTM model, the Facial-LSTM model improved by about 3%. This indicated that the expression mode helped eliminate EEG signals that contained few or no emotional features, enhancing emotion recognition accuracy. Compared with the Facial-LSTM model, the classification accuracy of the LSTM-CNN model improved by 3.7%, showing that the addition of facial expressions affected the EEG features to a certain extent. Therefore, using various modal features for emotion recognition conforms to human emotional expression. Furthermore, it improves feature diversity to facilitate further emotion recognition research.

The Anger of the Main Character in the Perempuan Bersampur Merah Novel by Intan Adaru: A Study of Literary Psychology

This study aims to describe (1) the form of anger of the main character in the novel "Perempuan Bersampur Merah" by Intan Andaru and (2) the factors of anger of the main character in the novel "Perempuan Bersampur Merah" by Intan Andaru, also describe (3) the psychological impact of the main character in the novel “Perempuan Bersampur Merah” by Intan Andaru. This research is a qualitative descriptive study. The subject of this research is the novel "Perempuan Bersampur Merah" by Intan Andaru. The method of data collection is done by reading and note-taking techniques. The data were analyzed by qualitative descriptive technique, which is a research procedure with descriptive data presented in the form of the author's speech in the novel "Perempuan Bersampur Merah" by Intan Andaru.. The results showed that (1) the form of anger of the main character in the novel "Perempuan Bersampur Merah" by Intan Andaru, namely the anger described by the author in the main character, anger is an expression of human emotions in venting dissatisfaction, disappointment or mistakes when there is an emotional turmoil that does not occur. controlled include revenge, curiosity, irritation, hurt and overflowing emotions (2) the factors of anger between characters in the novel "Perempuan Bersampur Merah" by Intan Andaru there are several factors, namely environmental factors, family factors, social factors. Not only that, anger also arises on the basis of feeling disappointed, irritated, disgusted and annoyed. (3) the psychological impact of the main character in the novel "Perempuan Bersampur Merah" by Intan Andaru caused several problems for the main character, namely being depressed, uncomfortable with their environment, potentially hurting themselves, interfering with children's relationships with parents, even with family, problems with friends peers, school environment, even the environment where the child lives.

On the Application of Information Technology in the Teaching of Ancient Poetry Recitation

Ancient poetry recitation teaching, as a course that requires high human literacy, emotional expression and knowledge reserve, how to enable teachers to improve the teaching mode and construct a recitation classroom that can more inspire students to learn initiative, has become a need Problems that the ancient Chinese teachers in universities and colleges focus on solving. This article starts with the importance of introducing information technology in ancient poetry recitation classes in colleges and universities, looking for specific teaching models, hoping to provide suggestions for other teachers.

Consumer responses toward symmetric versus asymmetric facial expression emojis

Facial expression emojis are commonly used in digital communications and marketing campaigns. However, it is less known how the design of emojis may affect consumer responses. To address this gap, this research examines the impact of emojis’ facial asymmetry levels on consumer judgments. Findings across four studies demonstrate that compared with their symmetric counterparts, asymmetric facial expression emojis are more likely to receive favorable consumer evaluations. This effect is driven by perceptions of human expression resemblance and emotional expression strength and tends to be more prominent among consumers with a higher level of emotional sensitivity. Moreover, marketing messages including an asymmetric (vs. a symmetric) emoji are more likely to generate positive consumer responses.

Deep learning based facial expression recognition using improved Cat Swarm Optimization

Human emotional facial expressions play a vital role in interpersonal relations. Automated facial expression recognition has always remained a challenging problem in real-life applications as people vary significantly in the way of showing their expressions. Recently various approaches have been proposed for automatically analyzing the facial expression of a person. In this paper, a novel approach to human facial expression recognition by applying a modified version of the Cat Swarm Optimization (CSO) algorithm, called Improved Cat Swarm Optimization (ICSO) algorithm is proposed. The input image given to the proposed system retrieves similar images from the dataset as well as identifies the person’s emotional state through facial expressions. Deep features present in the face image are extracted using Deep Convolution Neural Network (DCNN) approach. ICSO is proposed to select optimal features from the face image that can uniquely distinguish the facial expression of a person. Employing DCNN with ICSO improves the retrieval performance of the proposed system. Ensemble classifiers that employ Neural Network (NN) and Support Vector Machine (SVM) are implemented to classify facial expressions such as normal, happy, sad, surprise, fear and angry. The performance of the proposed system is evaluated using JAFFE, CK+, Pie datasets and some real-world images. The proposed system outperforms the existing system, thus achieving superior accuracy and reduced computation time.

Application and Research of Folk Music Composition Based on Artificial Intelligence Technology

Music is one of the important forms of human emotion expression. Using artificial methods and technologies to allow the machine to quickly identify optical scores and real-time music sounds, through the inference and optimization of music emotion models, obtain human music emotion expression patterns, and actively complete human-machine collaboration with intelligent composition, and other related services. The development of multi-source perception of affective artificial intelligence has important research value and practical significance. This article mainly integrates multiple models of existing artificial intelligence models (typed music models, Markov chain models, genetic algorithm models, neural network models, etc.) to improve the rule knowledge to form a practical and effective hybrid model. Its innovation lies in combining formulas and matrix data combinations to intelligently compose non-note units (reproducing structures) in automatic composition, so as to achieve harmony, audibility and intelligence of music.

REM versus Non-REM sleep disturbance specifically affects inter-specific emotion processing in family dogs (Canis familiaris)

Dogs have outstanding capabilities to read human emotional expressions, both vocal and facial. It has also been shown that positively versus negatively valenced dog-human social interactions substantially affect dogs’ subsequent sleep. In the present study, we manipulated dogs’ (N = 15, in a within subject design) sleep structure by specifically disrupting REM versus Non-REM sleep, while maintaining equal sleep efficiency (monitored via non-invasive polysomnography). We found that both the number of awakenings as well as relative Non-REM (but not relative REM) duration influenced dogs’ viewing patterns in a task where sad and happy human faces were simultaneously projected with sad or happy human voice playbacks. In accordance with the emotion laterality hypothesis, the interaction between sound valence and Non-REM sleep duration was specific to images projected to the left (regardless of image-sound congruency). These results reveal the first evidence of a causal link between sleep structure and inter-specific emotion-processing in the family dog.

Empower rumor events detection from Chinese microblogs with multi-type individual information

Online social media has become an ideal place in spreading rumor events with its convenience in communication and information dissemination, which raises the difficulty in debunking rumor events automatically. To deal with such a challenge, traditional classification approaches relying on manually labeled features have to face a daunting number of human efforts. With the consideration of the realness of a rumor event, it will be verified and authenticated with multi-type individual information, especially with individuals’ emotional expressions to events and their own credibility. This paper presents a novel two-layer GRU model for rumor events detection based on multi-type individual information (MII) and a dynamic time-series (DTS) algorithm, named as MII–DTS-GRU. Specifically, MII refers to adopt the sentiment dictionary to identify fine-grained human emotional expressions to events and fuse with the individual credibility. Besides, the DTS algorithm retains the time distribution of social events. Experimental results on Sina Weibo datasets show that our model achieves a high accuracy of 96.3% and demonstrate that our proposed MII–DTS-GRU model outperforms the state-of-the-art models on rumor events detection.

White matter correlates of hemi-face dominance in happy and sad expression.

The neural underpinnings of human emotional expression are thought to be unevenly distributed among the two brain hemispheres. However, little is known on the anatomy supporting this claim, particularly in the cerebral white matter. Here, we explored the relationship between hemi-face dominance in emotional expression and cerebral white matter asymmetries in 33 healthy participants. Measures of emotional expression were derived from pictures of the participant's faces in a 'happy smiling' and a 'sad frowning' conditions. Chimeric faces were constructed by mirroring right and left hemi-faces, as done in previous studies, resulting in a left mirrored and right mirrored chimeric face per picture. To gain measures of hemi-face dominance per participant, a jury of 20 additional participants rated which chimeric face shows the higher intensity of emotional expressivity, by marking a 155mm line between the two versions. Measures of the asymmetry of the uncinate, the cingulum and the three branches of superior longitudinal fasciculi were derived from diffusion-weighted imaging tractography dissections. Group effect analyses indicated that the degree of asymmetry in emotional expression was not as prominent as reported in the literature and showed a large inter-individual variability. The degree of asymmetry in emotional expression was, however, significantly associated with the asymmetries in connective properties of the fronto-temporal and fronto-parietal tracts, specifically the uncinate fasciculus and the first branch of the superior longitudinal fasciculus. Therefore, this result raises novel hypotheses on the relationship of specific white matter tracts and emotional expression, especially their role in mood disorders.

\u201cCan Computer Based Human-Likeness Endanger Humanness?\u201d \u2013 A Philosophical and Ethical Perspective on Digital Assistants Expressing Feelings They Can\u2019t Have\u201d

Digital assistants engage with us with increasingly human-like conversations, including the expression of human emotions with such utterances as “I am sorry…”, “I hope you enjoy…”, “I am grateful…”, or “I regret that…”. By 2021, digital assistants will outnumber humans. No one seems to stop to ask if creating more digital companions that appear increasingly human is really beneficial to the future of our species. In this essay, we pose the question: “How human should computer-based human-likeness appear?” We rely on the philosophy of humanness and the theory of speech acts to consider the long-term consequences of living with digital creatures that express human-like feelings. We argue that feelings are the very substance of our humanness and therefore are best reserved for human interaction.

THE ETHICS OF EMOTION IN AI SYSTEMS

Computational analyses of data pertaining to human emotional expression have a surprisingly long history and an increasingly critical role in social machine learning (ML) and artificial intelligence (AI) applications. Contemporary, quotidian, narrow AI/ML technologies are most frequently used by social media platforms for modeling and predicting human emotional expression as signals of interpersonal interaction and personal preference. Yet while the ethical and social impacts of ML/AI systems have of late become major topics of both public discussion and academic debate , the ethical dimensions of AI/ML analytics for emotional expression have been under-theorized in these conversations. In this paper, we connect contemporary technical methods for analyzing emotional expression via AI/ML with extant problems in the ethics of AI discourse, in doing so highlighting tensions within that broader discourse and implications for the application of emotion analysis in practice.

The affective facial recognition task: The influence of cognitive styles and exposure times

The main task of emotional facial recognition is to understand human emotion expression through the recognition of facial expressions, so as to achieve more effective communication and interpersonal communication. Therefore, facial recognition plays an important role in people's daily lives. In addition, the research of facial recognition is also helpful to understand the human perception processing mode, and promote the development of pattern recognition, cognitive science, neural network and other fields. With the development of cognitive science, facial recognition technology has been continuously improved, and emotional facial recognition tasks have received attention in the fields of pattern recognition and artificial intelligence, and have become a research hotspot. Among them, pattern recognition is a cognitive system applied to many fields. For the first time, we confirmed the effects of facial memory time, personal cognitive style, and emotions associated with the target face on facial recognition patterns. This study measured the impact of time, cognitive style, and emotional type of 62 qualified college students. The research results show that cognitive style and facial emotional content are of great significance for face pattern recognition. Specifically, students classified as “dependent” have achieved good results in face pattern recognition, and positive and negative strong emotional faces have left behind those who show neutral emotions. A deeper impression. Finally, an unusual phenomenon was discovered, which indicates that the shorter the time spent on the face of the memory, the higher the recognition score.

Empathy to emotional voices and the use of real-time fMRI to enhance activation of the anterior insula

The right anterior insula (AI), known to have a key role in the processing and understanding of social emotions, is activated during tasks that involve the act of empathising. Neurofeedback provides individuals with a visualisation of their own brain activity, enabling them to regulate and modify this activity. Following previous research investigating the ability of individuals to up-regulate right AI activity levels through neurofeedback, we investigated whether this could be similarly accomplished during an empathy task involving auditory stimuli of human positive and negative emotional expressions. Twenty participants, ten with feedback from right anterior insula and ten with feedback from a sham brain region, participated in two sessions that included sixteen neurofeedback runs and four transfer runs. Results showed that for the second session participants in the right AI neurofeedback group demonstrated better ability to up-regulate their right AI compared to the control group who received sham feedback. Examination of the relationship between individual participants’ empathic traits and their ability to up-regulate right AI activity showed that participants low on empathic traits produced a greater increase in activation of right AI by the end of training. Moreover, the response to positively valenced audio stimuli was greater than for negatively valenced stimuli. These results have implications for therapeutic training of empathy in populations with limited empathic response.

Human facial expression affects a dog’s response to conflicting directional gestural cues

There is growing scientific interest in both the ability of dogs to evaluate emotional cues and their response to social cueing, we therefore examined the interaction between these by investigating whether human facial expression impact on dogs’ approach preference to conflicting directional gestural signals. During testing, a human demonstrator simultaneously pointed in one direction and faced (looked towards) in another towards one of two food bowls placed on opposite sides of the demonstrator with either a happy, angry or neutral facial expression. Thirty-six pet dogs were assessed for their approach preference, approach time, alongside aspects of their temperament (positive/negative activation and impulsivity via validated questionnaires). Dogs significantly preferred to follow the ‘point’ over ‘face’ cue when the demonstrator displayed angry or neutral expressions but showed no significant preference when the demonstrator displayed a happy expression. Additionally, dogs scoring higher for impulsivity approached the chosen cue significantly faster than those with lower scores. The findings show that dogs integrate information available from human emotional facial expressions with directional gestural information in their response choices within dog-human interactions.

Why Collaborative Robots Must Be Social (and even Emotional) Actors

In this article, I address the question whether or not robots should be social actors and suggest that we do not have much choice but to construe collaborative robots as social actors. Social cues, including emotional displays, serve coordination functions in human interaction and therefore have to be used, even by robots, in order for long-term collaboration to succeed. While robots lack the experiential basis of emotional display, also in human interaction much emotional expression is part of conventional social practice; if robots are to participate in such social practices, they need to produce such signals as well. I conclude that if we aim to share our social spaces with robots, they better be social actors, which may even include the display of emotions. This finding is of empirical as well as philosophical relevance because it shifts the ethical discussion away from the question, how social collaborative robots should be, to the question, what kinds of human-robot collaborations we want.