In multi-modal emotion recognition,excessive reliance on historical context often impedes the detection of emotional shifts,while modality heterogeneity and unimodal noise limit recognition performance.Existing method...In multi-modal emotion recognition,excessive reliance on historical context often impedes the detection of emotional shifts,while modality heterogeneity and unimodal noise limit recognition performance.Existing methods struggle to dynamically adjust cross-modal complementary strength to optimize fusion quality and lack effective mechanisms to model the dynamic evolution of emotions.To address these issues,we propose a multi-level dynamic gating and emotion transfer framework for multi-modal emotion recognition.A dynamic gating mechanism is applied across unimodal encoding,cross-modal alignment,and emotion transfer modeling,substantially improving noise robustness and feature alignment.First,we construct a unimodal encoder based on gated recurrent units and feature-selection gating to suppress intra-modal noise and enhance contextual representation.Second,we design a gated-attention crossmodal encoder that dynamically calibrates the complementary contributions of visual and audio modalities to the dominant textual features and eliminates redundant information.Finally,we introduce a gated enhanced emotion transfer module that explicitly models the temporal dependence of emotional evolution in dialogues via transfer gating and optimizes continuity modeling with a comparative learning loss.Experimental results demonstrate that the proposed method outperforms state-of-the-art models on the public MELD and IEMOCAP datasets.展开更多
BACKGROUND Anxiety,depression,and other negative emotions are common among patients with chronic renal failure(CRF).Analyzing the factors related to negative emotions is necessary to provide targeted nursing care.AIM ...BACKGROUND Anxiety,depression,and other negative emotions are common among patients with chronic renal failure(CRF).Analyzing the factors related to negative emotions is necessary to provide targeted nursing care.AIM To explore the correlations among life satisfaction,pleasure levels,and negative emotions in patients with CRF.METHODS One hundred patients with CRF who received therapy at the First Affiliated Hospital of Jinzhou Medical University between December 2022 and February 2025 were included.The Depression,Anxiety,and Stress Scale(DASS-21),Satisfaction with Life Scale(SWLS),and Temporal Experience of Pleasure Scale(TEPS)were used to evaluate negative emotions,life satisfaction,and pleasure level,respectively.Pearson’s correlation coefficient analyzed the correlation between life satisfaction,pleasure level,and negative emotions.Linear regression analysis identified the factors affecting negative emotions.RESULTS The average DASS-21 score among patients with CRF was 51.90±2.30,with subscale scores of 17.90±1.50 for depression,18.53±1.18 for anxiety,and 15.47±2.36 for stress,all significantly higher than the domestic norm(P<0.05).The average SWLS score was 22.17±4.90.Correlation analysis revealed a negative correlation between the SWLS and total DASS-21 scores(P<0.05),but not with the individual depression,anxiety,or stress dimensions.The average TEPS score was 67.80±8.34.TEPS scores were negatively correlated with the DASS-21 score and the stress dimension(P<0.05),but not with depression or anxiety.Linear regression analysis showed that TEPS scores significantly influenced DASS-21 scores(P<0.05).CONCLUSION Patients with CRF experience high levels of negative emotions,which are negatively correlated with life satisfaction and pleasure.Furthermore,pleasure level had an impact on negative emotions.展开更多
BACKGROUND The prevalence of negative emotional states,such as anxiety and depression,has increased annually.Although personal habits are known to influence emotional regulation,the precise mechanisms underlying this ...BACKGROUND The prevalence of negative emotional states,such as anxiety and depression,has increased annually.Although personal habits are known to influence emotional regulation,the precise mechanisms underlying this relationship remain unclear.AIM To investigate emotion regulation habits impact on students negative emotions during lockdown,using the coronavirus disease 2019 pandemic as a case example.METHODS During the coronavirus disease 2019 lockdown,an online cross-sectional survey was conducted at a Chinese university.Emotional states were assessed using the Depression,Anxiety,and Stress Scale-21(DASS-21),while demographic data and emotion regulation habits were collected concurrently.Data analysis was performed using SPSS version 27.0 and includedχ^(2)-tests for intergroup comparisons,Spearman’s rank-order correlation coefficient analysis to examine associations,and stepwise linear regression modeling to explore the relationships between emotion regulation habits and emotional states.Statistical significance was set atα=0.05.RESULTS Among the 494 valid questionnaires analyzed,the prevalence rates of negative emotional states were as follows:Depression(65.0%),anxiety(69.4%),and stress(50.8%).DASS-21 scores(mean±SD)demonstrated significant symptomatology:Total(48.77±34.88),depression(16.21±12.18),anxiety(14.90±11.91),and stress(17.64±12.07).Significant positive intercorrelations were observed among all DASS-21 subscales(P<0.01).Regression analysis identified key predictors of negative emotions(P<0.05):Risk factors included late-night frequency and academic pressure,while protective factors were the frequency of parental contact and the number of same-gender friends.Additionally,compensatory spending and binge eating positively predicted all negative emotion scores(β>0,P<0.01),whereas appropriate recreational activities negatively predicted these scores(β<0,P<0.01).CONCLUSION High negative emotion prevalence occurred among confined students.Recreational activities were protective,while compensatory spending and binge eating were risk factors,necessitating guided emotion regulation.展开更多
To enhance speech emotion recognition capability,this study constructs a speech emotion recognition model integrating the adaptive acoustic mixup(AAM)and improved coordinate and shuffle attention(ICASA)methods.The AAM...To enhance speech emotion recognition capability,this study constructs a speech emotion recognition model integrating the adaptive acoustic mixup(AAM)and improved coordinate and shuffle attention(ICASA)methods.The AAM method optimizes data augmentation by combining a sample selection strategy and dynamic interpolation coefficients,thus enabling information fusion of speech data with different emotions at the acoustic level.The ICASA method enhances feature extraction capability through dynamic fusion of the improved coordinate attention(ICA)and shuffle attention(SA)techniques.The ICA technique reduces computational overhead by employing depth-separable convolution and an h-swish activation function and captures long-range dependencies of multi-scale time-frequency features using the attention weights.The SA technique promotes feature interaction through channel shuffling,which helps the model learn richer and more discriminative emotional features.Experimental results demonstrate that,compared to the baseline model,the proposed model improves the weighted accuracy by 5.42%and 4.54%,and the unweighted accuracy by 3.37%and 3.85%on the IEMOCAP and RAVDESS datasets,respectively.These improvements were confirmed to be statistically significant by independent samples t-tests,further supporting the practical reliability and applicability of the proposed model in real-world emotion-aware speech systems.展开更多
In computer vision and artificial intelligence,automatic facial expression-based emotion identification of humans has become a popular research and industry problem.Recent demonstrations and applications in several fi...In computer vision and artificial intelligence,automatic facial expression-based emotion identification of humans has become a popular research and industry problem.Recent demonstrations and applications in several fields,including computer games,smart homes,expression analysis,gesture recognition,surveillance films,depression therapy,patientmonitoring,anxiety,and others,have brought attention to its significant academic and commercial importance.This study emphasizes research that has only employed facial images for face expression recognition(FER),because facial expressions are a basic way that people communicate meaning to each other.The immense achievement of deep learning has resulted in a growing use of its much architecture to enhance efficiency.This review is on machine learning,deep learning,and hybrid methods’use of preprocessing,augmentation techniques,and feature extraction for temporal properties of successive frames of data.The following section gives a brief summary of assessment criteria that are accessible to the public and then compares them with benchmark results the most trustworthy way to assess FER-related research topics statistically.In this review,a brief synopsis of the subject matter may be beneficial for novices in the field of FER as well as seasoned scholars seeking fruitful avenues for further investigation.The information conveys fundamental knowledge and provides a comprehensive understanding of the most recent state-of-the-art research.展开更多
In recent years,gait-based emotion recognition has been widely applied in the field of computer vision.However,existing gait emotion recognition methods typically rely on complete human skeleton data,and their accurac...In recent years,gait-based emotion recognition has been widely applied in the field of computer vision.However,existing gait emotion recognition methods typically rely on complete human skeleton data,and their accuracy significantly declines when the data is occluded.To enhance the accuracy of gait emotion recognition under occlusion,this paper proposes a Multi-scale Suppression Graph ConvolutionalNetwork(MS-GCN).TheMS-GCN consists of three main components:Joint Interpolation Module(JI Moudle),Multi-scale Temporal Convolution Network(MS-TCN),and Suppression Graph Convolutional Network(SGCN).The JI Module completes the spatially occluded skeletal joints using the(K-Nearest Neighbors)KNN interpolation method.The MS-TCN employs convolutional kernels of various sizes to comprehensively capture the emotional information embedded in the gait,compensating for the temporal occlusion of gait information.The SGCN extracts more non-prominent human gait features by suppressing the extraction of key body part features,thereby reducing the negative impact of occlusion on emotion recognition results.The proposed method is evaluated on two comprehensive datasets:Emotion-Gait,containing 4227 real gaits from sources like BML,ICT-Pollick,and ELMD,and 1000 synthetic gaits generated using STEP-Gen technology,and ELMB,consisting of 3924 gaits,with 1835 labeled with emotions such as“Happy,”“Sad,”“Angry,”and“Neutral.”On the standard datasets Emotion-Gait and ELMB,the proposed method achieved accuracies of 0.900 and 0.896,respectively,attaining performance comparable to other state-ofthe-artmethods.Furthermore,on occlusion datasets,the proposedmethod significantly mitigates the performance degradation caused by occlusion compared to other methods,the accuracy is significantly higher than that of other methods.展开更多
With the rapid development of web technology,Social Networks(SNs)have become one of the most popular platforms for users to exchange views and to express their emotions.More and more people are used to commenting on a...With the rapid development of web technology,Social Networks(SNs)have become one of the most popular platforms for users to exchange views and to express their emotions.More and more people are used to commenting on a certain hot spot in SNs,resulting in a large amount of texts containing emotions.Textual Emotion Cause Extraction(TECE)aims to automatically extract causes for a certain emotion in texts,which is an important research issue in natural language processing.It is different from the previous tasks of emotion recognition and emotion classification.In addition,it is not limited to the shallow-level emotion classification of text,but to trace the emotion source.In this paper,we provide a survey for TECE.First,we introduce the development process and classification of TECE.Then,we discuss the existing methods and key factors for TECE.Finally,we enumerate the challenges and developing trend for TECE.展开更多
This study investigated the impact of problematic mobile phone use(PMPU)on emotion recognition.The PMPU levels of 150 participants were measured using the standardized SAS-SV scale.Based on the SAS-SV cutoff scores,pa...This study investigated the impact of problematic mobile phone use(PMPU)on emotion recognition.The PMPU levels of 150 participants were measured using the standardized SAS-SV scale.Based on the SAS-SV cutoff scores,participants were divided into PMPU and Control groups.These participants completed two emotion recognition experiments involving facial emotion stimuli that had been manipulated to varying emotional intensities using Morph software.Experiment 1(n=75)assessed differences in facial emotion detection accuracy.Experiment 2(n=75),based on signal detection theory,examined differences in hit and false alarm rates across emotional expressions.The results showed that PMPU users demonstrated higher recognition accuracy rates for disgust faces but lower accuracy for happy faces.This indicates a tendency among PMPU users to prioritize specific negative emotions and may have impaired perception of positive emotions.Practically,incorporating diverse emotional stimuli into PMPU intervention may help alleviate the negative emotional focus bias associated with excessive mobile devices use.展开更多
“The blood-washed film will never lie.”When that line was spoken in Dead to Rights,the cinema seemed frozen in a deeper silence than I had ever experienced.It pierced the air with a truth that could not be softened,...“The blood-washed film will never lie.”When that line was spoken in Dead to Rights,the cinema seemed frozen in a deeper silence than I had ever experienced.It pierced the air with a truth that could not be softened,and I felt my chest tighten as if the words had been spoken directly to me.At that moment,I was not merely a spectator of a film,but a witness called to remember.The trembling voice of the actor,the stark finality of the line-it overwhelmed me with an emotion too heavy for words,a blend of grief,anger,and responsibility.展开更多
The Guide to Learning and Development for Children Aged 3–6 states that“a pleasant emotion is one of the important indicators of children’s physical and mental health,and it is also the foundation for learning and ...The Guide to Learning and Development for Children Aged 3–6 states that“a pleasant emotion is one of the important indicators of children’s physical and mental health,and it is also the foundation for learning and development in other areas.”Emotional health in early childhood plays a significant role in their future development.This article focuses on understanding the characteristics of young children’s emotions and the factors that affect their emotional management.Simultaneously,it proposes effective methods for families and kindergartens to jointly protect children’s emotional and mental health,providing a healthy and positive growth environment for preschool children,and jointly supporting their growth.展开更多
With the increasing popularity of mobile internet devices,speech emotion recognition has become a convenient and valuable means of human-computer interaction.The performance of speech emotion recognition depends on th...With the increasing popularity of mobile internet devices,speech emotion recognition has become a convenient and valuable means of human-computer interaction.The performance of speech emotion recognition depends on the discriminating and emotion-related utterance-level representations extracted from speech.Moreover,sufficient data are required to model the relationship between emotional states and speech.Mainstream emotion recognition methods cannot avoid the influence of the silence period in speech,and environmental noise significantly affects the recognition performance.This study intends to supplement the silence periods with removed speech information and applies segmentwise multilayer perceptrons to enhance the utterance-level representation aggregation.In addition,improved semisupervised learning is employed to overcome the prob-lem of data scarcity.Particular experiments are conducted to evaluate the proposed method on the IEMOCAP corpus,which reveals that it achieves 68.0%weighted accuracy and 68.8%unweighted accuracy in four emotion classifications.The experimental results demonstrate that the proposed method aggregates utterance-level more effectively and that semisupervised learning enhances the performance of our method.展开更多
In the successive rise of the metaverse and artificial intelligence(AI),rationalism and emotionalism have consistently manifested as symptoms of modernity throughout their developmental trajectories.This paper argues ...In the successive rise of the metaverse and artificial intelligence(AI),rationalism and emotionalism have consistently manifested as symptoms of modernity throughout their developmental trajectories.This paper argues that the achievements and crises of both fields signify the triumph of rationalism in the context of deepening modernity,while simultaneously harboring an intrinsic impetus and possibility for transitioning from rationalism to emotionalism.This dynamic serves as a quintessential representation of modernity’s crises and their transcendence.Centered on embodied cognitive science,AI and the metaverse—rooted in rationalism—now face challenges in shifting toward emotionalism,revealing their inadequacy in addressing this shift.Humanity must explore new modernity-deepening paradigms grounded in emotionalism to confront and transcend the potential crises posed by the metaverse and AI.展开更多
Objectives:Adults with cataracts are often reported with mental health issues,which has driven researchers to identify modifiable factors so that effective intervention programs can be timely implemented.Thus,we inves...Objectives:Adults with cataracts are often reported with mental health issues,which has driven researchers to identify modifiable factors so that effective intervention programs can be timely implemented.Thus,we investigated associations of physical activity(PA)and sedentary behavior(SB)with stress,anxiety,and sleep problems among adultswith cataracts.Methods:In this cross-sectional study,a total of 2219 participantswith cataracts completed self-reported measures on demographic characteristics(e.g.,age and sex),PA,SB,anxiety,stress and sleep problems.Multiple linear regression and logistic analyses adjusted for covariates were employed to examine the associations of PA and SB with outcomes of interest.Results:Meeting PA recommendation was significantly associated with lower stress score(β=−2.920,95%CI:−3.880 to−1.959;p<0.001),a 51.2%reduction in the odds of sleep problems(OR=0.488,95%CI:0.389 to 0.612;p<0.001).Limiting SB to≤8 h/day was significantly associated with reduced stress score(−5.191,95%CI:−6.378 to−4.004;p<0.001),lower odds of anxiety symptoms(OR=0.481,95%CI:0.354 to 0.655;p<0.001),and sleep problems(OR=0.540,95%CI:0.420 to 0.693;p<0.001).The greatest benefit appeared when both PA and SB recommendations were achieved simultaneously.Compared with individuals who met neither recommendation,those who were sufficiently active and sat less than 8 h/day showed a 9.307-point lower stress score(95%CI:−11.12 to−7.49;p<0.001),a 54.9%lower odds of anxiety symptoms(OR=0.451,95%CI:0.262 to 0.776;p=0.004),and a 66.4%lower odds of sleep problems(OR=0.336,95%CI:0.206 to 0.550;p<0.001).Conclusions:Meeting PA and SB recommendations could provide substantial psychosocial benefits for adults with cataracts.展开更多
The adoption of content and language integrated learning(CLIL)practices has expanded in recent years as higher education institutions adopt a top-down English medium of instruction(EMI)language policy in the hope of e...The adoption of content and language integrated learning(CLIL)practices has expanded in recent years as higher education institutions adopt a top-down English medium of instruction(EMI)language policy in the hope of entering the international knowledge market(De Costa et al.,2022;Isidro&Lasagabaster,2019).However,research focusing on the effects of EMI policy on content teachers needing to implement CLIL,especially within trilingual contexts such as Kazakhstan,has been marginal despite drastic alterations to teachers’professional context and expectations(Karabassova,2022b).Such changes may result in teachers’feelings of professional vulnerability-an emotion that often arises when changes in professional expectations and professional context disrupt one’s professional identity and pedagogical practices(Kelchtermans,2009).Our case study focuses on the professional vulnerability experienced by a Kazakhstani in-service teacher as she negotiated a CLIL pedagogy for the first time.Relying on semi-structured interviews,recorded classroom observation,field notes,and developed material,our findings highlight how macro(e.g.,societal)and meso(e.g.,institutional)language policies can affect teachers’lived experiences and pedagogical practices within their classrooms.Lastly,we provide ways in which administrators can assist teachers in overcoming professional vulnerability as institutions adopt language policies such as CLIL.展开更多
Background:The Canadian 24-h movement guidelines(24-HMG)emphasize the holistic consideration of physical activity(PA),sedentary behavior,and sleep in shaping health outcomes.This study aimed to examine the association...Background:The Canadian 24-h movement guidelines(24-HMG)emphasize the holistic consideration of physical activity(PA),sedentary behavior,and sleep in shaping health outcomes.This study aimed to examine the associations between meeting 24-HMG and emotion regulation-related indicators among children and adolescents.Methods:A total of 534 Chinese children and adolescents aged 12.94±1.10 years(49.81%males)participated in this study and completed self-report measures assessing 24-h movement behaviors,emotion regulation strategies,emotion regulation flexibility,and regulatory emotional self-efficacy.Results:Only 7.12% of theparticipants adhered to two or all three guidelines.The number of guidelines met was positively associated with the use of emotion regulation strategies,emotion regulation flexibility,and regulatory emotional self-efficacy.Compared with meeting none of the guidelines,participants whomet one ormore guidelines reported significantly better performance in these outcomes.Conclusion:Meeting 24-HMG was associated with superior emotion regulation in children and adolescents.The importance of engaging in regular PA,limiting recreational screen time,and getting enough sleep should be highlighted for fostering emotion regulation in this demographic.展开更多
Emotion recognition plays a crucial role in various fields and is a key task in natural language processing (NLP). The objective is to identify and interpret emotional expressions in text. However, traditional emotion...Emotion recognition plays a crucial role in various fields and is a key task in natural language processing (NLP). The objective is to identify and interpret emotional expressions in text. However, traditional emotion recognition approaches often struggle in few-shot cross-domain scenarios due to their limited capacity to generalize semantic features across different domains. Additionally, these methods face challenges in accurately capturing complex emotional states, particularly those that are subtle or implicit. To overcome these limitations, we introduce a novel approach called Dual-Task Contrastive Meta-Learning (DTCML). This method combines meta-learning and contrastive learning to improve emotion recognition. Meta-learning enhances the model’s ability to generalize to new emotional tasks, while instance contrastive learning further refines the model by distinguishing unique features within each category, enabling it to better differentiate complex emotional expressions. Prototype contrastive learning, in turn, helps the model address the semantic complexity of emotions across different domains, enabling the model to learn fine-grained emotions expression. By leveraging dual tasks, DTCML learns from two domains simultaneously, the model is encouraged to learn more diverse and generalizable emotions features, thereby improving its cross-domain adaptability and robustness, and enhancing its generalization ability. We evaluated the performance of DTCML across four cross-domain settings, and the results show that our method outperforms the best baseline by 5.88%, 12.04%, 8.49%, and 8.40% in terms of accuracy.展开更多
The present study explores the importance of developing metaphorical thinking skills in students within the framework of English as a Foreign Language(EFL)reading courses at the tertiary educational level.Metaphorical...The present study explores the importance of developing metaphorical thinking skills in students within the framework of English as a Foreign Language(EFL)reading courses at the tertiary educational level.Metaphorical thinking is viewed as the ability to envisage the world figuratively,perceive associatively,and express oneself creatively.It is crucial to recognize metaphors in texts,interpret the complex images they evoke,and generate new metaphors.It is especially needful in the current era of clip thinking and fragmented information processing when students often approach content superficially rather than comprehensively,leading to decreased cognitive activity and a diminished capacity to understand literature.To foster metaphorical thinking,the paper suggests building a text associative-semantic field focusing on metaphors.Due to its hierarchical structure,which can be envisioned as a dense nucleus surrounded by a central region of synonyms and further enveloped by a periphery of more loosely associated linguistic units,the text associative-semantic field is seen as a potent solution for facilitating improved visualization and more holistic comprehension of information,allowing students for expanding their vocabulary and strengthening associative connections.Notably,the study highlights analyzing the metaphors of emotional states as they contribute significantly to a more profound interpretation of the text,understanding the writer’s unique style,deepening the students’engagement with the book,and expanding their emotional experiences.展开更多
The rapid growth of digital data necessitates advanced natural language processing(NLP)models like BERT(Bidi-rectional Encoder Representations from Transformers),known for its superior performance in text classificati...The rapid growth of digital data necessitates advanced natural language processing(NLP)models like BERT(Bidi-rectional Encoder Representations from Transformers),known for its superior performance in text classification.However,BERT’s size and computational demands limit its practicality,especially in resource-constrained settings.This research compresses the BERT base model for Bengali emotion classification through knowledge distillation(KD),pruning,and quantization techniques.Despite Bengali being the sixth most spoken language globally,NLP research in this area is limited.Our approach addresses this gap by creating an efficient BERT-based model for Bengali text.We have explored 20 combinations for KD,quantization,and pruning,resulting in improved speedup,fewer parameters,and reduced memory size.Our best results demonstrate significant improvements in both speed and efficiency.For instance,in the case of mBERT,we achieved a 3.87×speedup and 4×compression ratio with a combination of Distil+Prune+Quant that reduced parameters from 178 to 46 M,while the memory size decreased from 711 to 178 MB.These results offer scalable solutions for NLP tasks in various languages and advance the field of model compression,making these models suitable for real-world applications in resource-limited environments.展开更多
This study aimed to determine the reliability,validity and measurement invariance of scores from the Difficulties in Emotion Regulation Scale-8 in Chinese context.A total of 1114 Chinese adolescents were participants ...This study aimed to determine the reliability,validity and measurement invariance of scores from the Difficulties in Emotion Regulation Scale-8 in Chinese context.A total of 1114 Chinese adolescents were participants in three phases:N=424 for the initial DERS-8 measure completion;N=586 the DERS-8,General Anxiety Disorder Scale,Depression Scale and Emotion Regulation Scale completion,with an interval of one month.Then an additional 104 adolescents also completed DERS-8,General Anxiety Disorder Scale,Depression Scale and Emotion Regulation Scale.Both exploratory and confirmatory factor analyses confirmed the one-factor model of the scale,and the fitness indicators wereχ^(2)/df=4.05,RMSEA=0.07,CFI=0.98,and TLI=0.97.Each item of the DERS-8 had good discrimination.The internal consistency reliability coefficient,split-half reliability coefficient and test-retest reliability coefficient of the scale scores were 0.90,0.87 and 0.66,respectively.The findings suggest the Chinese version of the DERS-8 is a reliable measure of difficulty of emotion regulation in Chinese adolescents.展开更多
基金funded by“the Fanying Special Program of the National Natural Science Foundation of China,grant number 62341307”“the Scientific research project of Jiangxi Provincial Department of Education,grant number GJJ200839”“theDoctoral startup fund of JiangxiUniversity of Technology,grant number 205200100402”.
文摘In multi-modal emotion recognition,excessive reliance on historical context often impedes the detection of emotional shifts,while modality heterogeneity and unimodal noise limit recognition performance.Existing methods struggle to dynamically adjust cross-modal complementary strength to optimize fusion quality and lack effective mechanisms to model the dynamic evolution of emotions.To address these issues,we propose a multi-level dynamic gating and emotion transfer framework for multi-modal emotion recognition.A dynamic gating mechanism is applied across unimodal encoding,cross-modal alignment,and emotion transfer modeling,substantially improving noise robustness and feature alignment.First,we construct a unimodal encoder based on gated recurrent units and feature-selection gating to suppress intra-modal noise and enhance contextual representation.Second,we design a gated-attention crossmodal encoder that dynamically calibrates the complementary contributions of visual and audio modalities to the dominant textual features and eliminates redundant information.Finally,we introduce a gated enhanced emotion transfer module that explicitly models the temporal dependence of emotional evolution in dialogues via transfer gating and optimizes continuity modeling with a comparative learning loss.Experimental results demonstrate that the proposed method outperforms state-of-the-art models on the public MELD and IEMOCAP datasets.
文摘BACKGROUND Anxiety,depression,and other negative emotions are common among patients with chronic renal failure(CRF).Analyzing the factors related to negative emotions is necessary to provide targeted nursing care.AIM To explore the correlations among life satisfaction,pleasure levels,and negative emotions in patients with CRF.METHODS One hundred patients with CRF who received therapy at the First Affiliated Hospital of Jinzhou Medical University between December 2022 and February 2025 were included.The Depression,Anxiety,and Stress Scale(DASS-21),Satisfaction with Life Scale(SWLS),and Temporal Experience of Pleasure Scale(TEPS)were used to evaluate negative emotions,life satisfaction,and pleasure level,respectively.Pearson’s correlation coefficient analyzed the correlation between life satisfaction,pleasure level,and negative emotions.Linear regression analysis identified the factors affecting negative emotions.RESULTS The average DASS-21 score among patients with CRF was 51.90±2.30,with subscale scores of 17.90±1.50 for depression,18.53±1.18 for anxiety,and 15.47±2.36 for stress,all significantly higher than the domestic norm(P<0.05).The average SWLS score was 22.17±4.90.Correlation analysis revealed a negative correlation between the SWLS and total DASS-21 scores(P<0.05),but not with the individual depression,anxiety,or stress dimensions.The average TEPS score was 67.80±8.34.TEPS scores were negatively correlated with the DASS-21 score and the stress dimension(P<0.05),but not with depression or anxiety.Linear regression analysis showed that TEPS scores significantly influenced DASS-21 scores(P<0.05).CONCLUSION Patients with CRF experience high levels of negative emotions,which are negatively correlated with life satisfaction and pleasure.Furthermore,pleasure level had an impact on negative emotions.
文摘BACKGROUND The prevalence of negative emotional states,such as anxiety and depression,has increased annually.Although personal habits are known to influence emotional regulation,the precise mechanisms underlying this relationship remain unclear.AIM To investigate emotion regulation habits impact on students negative emotions during lockdown,using the coronavirus disease 2019 pandemic as a case example.METHODS During the coronavirus disease 2019 lockdown,an online cross-sectional survey was conducted at a Chinese university.Emotional states were assessed using the Depression,Anxiety,and Stress Scale-21(DASS-21),while demographic data and emotion regulation habits were collected concurrently.Data analysis was performed using SPSS version 27.0 and includedχ^(2)-tests for intergroup comparisons,Spearman’s rank-order correlation coefficient analysis to examine associations,and stepwise linear regression modeling to explore the relationships between emotion regulation habits and emotional states.Statistical significance was set atα=0.05.RESULTS Among the 494 valid questionnaires analyzed,the prevalence rates of negative emotional states were as follows:Depression(65.0%),anxiety(69.4%),and stress(50.8%).DASS-21 scores(mean±SD)demonstrated significant symptomatology:Total(48.77±34.88),depression(16.21±12.18),anxiety(14.90±11.91),and stress(17.64±12.07).Significant positive intercorrelations were observed among all DASS-21 subscales(P<0.01).Regression analysis identified key predictors of negative emotions(P<0.05):Risk factors included late-night frequency and academic pressure,while protective factors were the frequency of parental contact and the number of same-gender friends.Additionally,compensatory spending and binge eating positively predicted all negative emotion scores(β>0,P<0.01),whereas appropriate recreational activities negatively predicted these scores(β<0,P<0.01).CONCLUSION High negative emotion prevalence occurred among confined students.Recreational activities were protective,while compensatory spending and binge eating were risk factors,necessitating guided emotion regulation.
基金supported by the National Natural Science Foundation of China under Grant No.12204062the Natural Science Foundation of Shandong Province under Grant No.ZR2022MF330。
文摘To enhance speech emotion recognition capability,this study constructs a speech emotion recognition model integrating the adaptive acoustic mixup(AAM)and improved coordinate and shuffle attention(ICASA)methods.The AAM method optimizes data augmentation by combining a sample selection strategy and dynamic interpolation coefficients,thus enabling information fusion of speech data with different emotions at the acoustic level.The ICASA method enhances feature extraction capability through dynamic fusion of the improved coordinate attention(ICA)and shuffle attention(SA)techniques.The ICA technique reduces computational overhead by employing depth-separable convolution and an h-swish activation function and captures long-range dependencies of multi-scale time-frequency features using the attention weights.The SA technique promotes feature interaction through channel shuffling,which helps the model learn richer and more discriminative emotional features.Experimental results demonstrate that,compared to the baseline model,the proposed model improves the weighted accuracy by 5.42%and 4.54%,and the unweighted accuracy by 3.37%and 3.85%on the IEMOCAP and RAVDESS datasets,respectively.These improvements were confirmed to be statistically significant by independent samples t-tests,further supporting the practical reliability and applicability of the proposed model in real-world emotion-aware speech systems.
文摘In computer vision and artificial intelligence,automatic facial expression-based emotion identification of humans has become a popular research and industry problem.Recent demonstrations and applications in several fields,including computer games,smart homes,expression analysis,gesture recognition,surveillance films,depression therapy,patientmonitoring,anxiety,and others,have brought attention to its significant academic and commercial importance.This study emphasizes research that has only employed facial images for face expression recognition(FER),because facial expressions are a basic way that people communicate meaning to each other.The immense achievement of deep learning has resulted in a growing use of its much architecture to enhance efficiency.This review is on machine learning,deep learning,and hybrid methods’use of preprocessing,augmentation techniques,and feature extraction for temporal properties of successive frames of data.The following section gives a brief summary of assessment criteria that are accessible to the public and then compares them with benchmark results the most trustworthy way to assess FER-related research topics statistically.In this review,a brief synopsis of the subject matter may be beneficial for novices in the field of FER as well as seasoned scholars seeking fruitful avenues for further investigation.The information conveys fundamental knowledge and provides a comprehensive understanding of the most recent state-of-the-art research.
基金supported by the National Natural Science Foundation of China(62272049,62236006,62172045)the Key Projects of Beijing Union University(ZKZD202301).
文摘In recent years,gait-based emotion recognition has been widely applied in the field of computer vision.However,existing gait emotion recognition methods typically rely on complete human skeleton data,and their accuracy significantly declines when the data is occluded.To enhance the accuracy of gait emotion recognition under occlusion,this paper proposes a Multi-scale Suppression Graph ConvolutionalNetwork(MS-GCN).TheMS-GCN consists of three main components:Joint Interpolation Module(JI Moudle),Multi-scale Temporal Convolution Network(MS-TCN),and Suppression Graph Convolutional Network(SGCN).The JI Module completes the spatially occluded skeletal joints using the(K-Nearest Neighbors)KNN interpolation method.The MS-TCN employs convolutional kernels of various sizes to comprehensively capture the emotional information embedded in the gait,compensating for the temporal occlusion of gait information.The SGCN extracts more non-prominent human gait features by suppressing the extraction of key body part features,thereby reducing the negative impact of occlusion on emotion recognition results.The proposed method is evaluated on two comprehensive datasets:Emotion-Gait,containing 4227 real gaits from sources like BML,ICT-Pollick,and ELMD,and 1000 synthetic gaits generated using STEP-Gen technology,and ELMB,consisting of 3924 gaits,with 1835 labeled with emotions such as“Happy,”“Sad,”“Angry,”and“Neutral.”On the standard datasets Emotion-Gait and ELMB,the proposed method achieved accuracies of 0.900 and 0.896,respectively,attaining performance comparable to other state-ofthe-artmethods.Furthermore,on occlusion datasets,the proposedmethod significantly mitigates the performance degradation caused by occlusion compared to other methods,the accuracy is significantly higher than that of other methods.
基金partially supported by the National Natural Science Foundation of China under Grant No.62372121the Ministry of education of Humanities and Social Science project under Grant No.20YJAZH118+1 种基金the National Key Research and Development Program of China under Grant No.2020YFB1005804the MOE Project at Center for Linguistics and Applied Linguistics,Guangdong University of Foreign Studies。
文摘With the rapid development of web technology,Social Networks(SNs)have become one of the most popular platforms for users to exchange views and to express their emotions.More and more people are used to commenting on a certain hot spot in SNs,resulting in a large amount of texts containing emotions.Textual Emotion Cause Extraction(TECE)aims to automatically extract causes for a certain emotion in texts,which is an important research issue in natural language processing.It is different from the previous tasks of emotion recognition and emotion classification.In addition,it is not limited to the shallow-level emotion classification of text,but to trace the emotion source.In this paper,we provide a survey for TECE.First,we introduce the development process and classification of TECE.Then,we discuss the existing methods and key factors for TECE.Finally,we enumerate the challenges and developing trend for TECE.
基金supported by the National Social Science Fund of China(Grant Number:20BSH134).
文摘This study investigated the impact of problematic mobile phone use(PMPU)on emotion recognition.The PMPU levels of 150 participants were measured using the standardized SAS-SV scale.Based on the SAS-SV cutoff scores,participants were divided into PMPU and Control groups.These participants completed two emotion recognition experiments involving facial emotion stimuli that had been manipulated to varying emotional intensities using Morph software.Experiment 1(n=75)assessed differences in facial emotion detection accuracy.Experiment 2(n=75),based on signal detection theory,examined differences in hit and false alarm rates across emotional expressions.The results showed that PMPU users demonstrated higher recognition accuracy rates for disgust faces but lower accuracy for happy faces.This indicates a tendency among PMPU users to prioritize specific negative emotions and may have impaired perception of positive emotions.Practically,incorporating diverse emotional stimuli into PMPU intervention may help alleviate the negative emotional focus bias associated with excessive mobile devices use.
文摘“The blood-washed film will never lie.”When that line was spoken in Dead to Rights,the cinema seemed frozen in a deeper silence than I had ever experienced.It pierced the air with a truth that could not be softened,and I felt my chest tighten as if the words had been spoken directly to me.At that moment,I was not merely a spectator of a film,but a witness called to remember.The trembling voice of the actor,the stark finality of the line-it overwhelmed me with an emotion too heavy for words,a blend of grief,anger,and responsibility.
文摘The Guide to Learning and Development for Children Aged 3–6 states that“a pleasant emotion is one of the important indicators of children’s physical and mental health,and it is also the foundation for learning and development in other areas.”Emotional health in early childhood plays a significant role in their future development.This article focuses on understanding the characteristics of young children’s emotions and the factors that affect their emotional management.Simultaneously,it proposes effective methods for families and kindergartens to jointly protect children’s emotional and mental health,providing a healthy and positive growth environment for preschool children,and jointly supporting their growth.
文摘With the increasing popularity of mobile internet devices,speech emotion recognition has become a convenient and valuable means of human-computer interaction.The performance of speech emotion recognition depends on the discriminating and emotion-related utterance-level representations extracted from speech.Moreover,sufficient data are required to model the relationship between emotional states and speech.Mainstream emotion recognition methods cannot avoid the influence of the silence period in speech,and environmental noise significantly affects the recognition performance.This study intends to supplement the silence periods with removed speech information and applies segmentwise multilayer perceptrons to enhance the utterance-level representation aggregation.In addition,improved semisupervised learning is employed to overcome the prob-lem of data scarcity.Particular experiments are conducted to evaluate the proposed method on the IEMOCAP corpus,which reveals that it achieves 68.0%weighted accuracy and 68.8%unweighted accuracy in four emotion classifications.The experimental results demonstrate that the proposed method aggregates utterance-level more effectively and that semisupervised learning enhances the performance of our method.
基金supported by the China Metaverse and Digital Talent Development Initiative and the general project of the National Social Science Foundation of China titled“Theoretical Interpretation of Advertising Messaging and the Development of a Typical Case Database”(19BXW085).
文摘In the successive rise of the metaverse and artificial intelligence(AI),rationalism and emotionalism have consistently manifested as symptoms of modernity throughout their developmental trajectories.This paper argues that the achievements and crises of both fields signify the triumph of rationalism in the context of deepening modernity,while simultaneously harboring an intrinsic impetus and possibility for transitioning from rationalism to emotionalism.This dynamic serves as a quintessential representation of modernity’s crises and their transcendence.Centered on embodied cognitive science,AI and the metaverse—rooted in rationalism—now face challenges in shifting toward emotionalism,revealing their inadequacy in addressing this shift.Humanity must explore new modernity-deepening paradigms grounded in emotionalism to confront and transcend the potential crises posed by the metaverse and AI.
文摘Objectives:Adults with cataracts are often reported with mental health issues,which has driven researchers to identify modifiable factors so that effective intervention programs can be timely implemented.Thus,we investigated associations of physical activity(PA)and sedentary behavior(SB)with stress,anxiety,and sleep problems among adultswith cataracts.Methods:In this cross-sectional study,a total of 2219 participantswith cataracts completed self-reported measures on demographic characteristics(e.g.,age and sex),PA,SB,anxiety,stress and sleep problems.Multiple linear regression and logistic analyses adjusted for covariates were employed to examine the associations of PA and SB with outcomes of interest.Results:Meeting PA recommendation was significantly associated with lower stress score(β=−2.920,95%CI:−3.880 to−1.959;p<0.001),a 51.2%reduction in the odds of sleep problems(OR=0.488,95%CI:0.389 to 0.612;p<0.001).Limiting SB to≤8 h/day was significantly associated with reduced stress score(−5.191,95%CI:−6.378 to−4.004;p<0.001),lower odds of anxiety symptoms(OR=0.481,95%CI:0.354 to 0.655;p<0.001),and sleep problems(OR=0.540,95%CI:0.420 to 0.693;p<0.001).The greatest benefit appeared when both PA and SB recommendations were achieved simultaneously.Compared with individuals who met neither recommendation,those who were sufficiently active and sat less than 8 h/day showed a 9.307-point lower stress score(95%CI:−11.12 to−7.49;p<0.001),a 54.9%lower odds of anxiety symptoms(OR=0.451,95%CI:0.262 to 0.776;p=0.004),and a 66.4%lower odds of sleep problems(OR=0.336,95%CI:0.206 to 0.550;p<0.001).Conclusions:Meeting PA and SB recommendations could provide substantial psychosocial benefits for adults with cataracts.
基金funding from the U.S.-Kazakhstan University Partnerships program funded by the U.S.Mission to Kazakhstan and administered by American Councils[Award number SKZ100-19-CA-0149].
文摘The adoption of content and language integrated learning(CLIL)practices has expanded in recent years as higher education institutions adopt a top-down English medium of instruction(EMI)language policy in the hope of entering the international knowledge market(De Costa et al.,2022;Isidro&Lasagabaster,2019).However,research focusing on the effects of EMI policy on content teachers needing to implement CLIL,especially within trilingual contexts such as Kazakhstan,has been marginal despite drastic alterations to teachers’professional context and expectations(Karabassova,2022b).Such changes may result in teachers’feelings of professional vulnerability-an emotion that often arises when changes in professional expectations and professional context disrupt one’s professional identity and pedagogical practices(Kelchtermans,2009).Our case study focuses on the professional vulnerability experienced by a Kazakhstani in-service teacher as she negotiated a CLIL pedagogy for the first time.Relying on semi-structured interviews,recorded classroom observation,field notes,and developed material,our findings highlight how macro(e.g.,societal)and meso(e.g.,institutional)language policies can affect teachers’lived experiences and pedagogical practices within their classrooms.Lastly,we provide ways in which administrators can assist teachers in overcoming professional vulnerability as institutions adopt language policies such as CLIL.
基金supported by Zhejiang Provincial Social Science Funding(22NDJC050YB).
文摘Background:The Canadian 24-h movement guidelines(24-HMG)emphasize the holistic consideration of physical activity(PA),sedentary behavior,and sleep in shaping health outcomes.This study aimed to examine the associations between meeting 24-HMG and emotion regulation-related indicators among children and adolescents.Methods:A total of 534 Chinese children and adolescents aged 12.94±1.10 years(49.81%males)participated in this study and completed self-report measures assessing 24-h movement behaviors,emotion regulation strategies,emotion regulation flexibility,and regulatory emotional self-efficacy.Results:Only 7.12% of theparticipants adhered to two or all three guidelines.The number of guidelines met was positively associated with the use of emotion regulation strategies,emotion regulation flexibility,and regulatory emotional self-efficacy.Compared with meeting none of the guidelines,participants whomet one ormore guidelines reported significantly better performance in these outcomes.Conclusion:Meeting 24-HMG was associated with superior emotion regulation in children and adolescents.The importance of engaging in regular PA,limiting recreational screen time,and getting enough sleep should be highlighted for fostering emotion regulation in this demographic.
基金supported by the ScientificResearch and Innovation Team Program of Sichuan University of Science and Technology(No.SUSE652A006)Sichuan Key Provincial Research Base of Intelligent Tourism(ZHYJ22-03)In addition,it is also listed as a project of Sichuan Provincial Science and Technology Programme(2022YFG0028).
文摘Emotion recognition plays a crucial role in various fields and is a key task in natural language processing (NLP). The objective is to identify and interpret emotional expressions in text. However, traditional emotion recognition approaches often struggle in few-shot cross-domain scenarios due to their limited capacity to generalize semantic features across different domains. Additionally, these methods face challenges in accurately capturing complex emotional states, particularly those that are subtle or implicit. To overcome these limitations, we introduce a novel approach called Dual-Task Contrastive Meta-Learning (DTCML). This method combines meta-learning and contrastive learning to improve emotion recognition. Meta-learning enhances the model’s ability to generalize to new emotional tasks, while instance contrastive learning further refines the model by distinguishing unique features within each category, enabling it to better differentiate complex emotional expressions. Prototype contrastive learning, in turn, helps the model address the semantic complexity of emotions across different domains, enabling the model to learn fine-grained emotions expression. By leveraging dual tasks, DTCML learns from two domains simultaneously, the model is encouraged to learn more diverse and generalizable emotions features, thereby improving its cross-domain adaptability and robustness, and enhancing its generalization ability. We evaluated the performance of DTCML across four cross-domain settings, and the results show that our method outperforms the best baseline by 5.88%, 12.04%, 8.49%, and 8.40% in terms of accuracy.
文摘The present study explores the importance of developing metaphorical thinking skills in students within the framework of English as a Foreign Language(EFL)reading courses at the tertiary educational level.Metaphorical thinking is viewed as the ability to envisage the world figuratively,perceive associatively,and express oneself creatively.It is crucial to recognize metaphors in texts,interpret the complex images they evoke,and generate new metaphors.It is especially needful in the current era of clip thinking and fragmented information processing when students often approach content superficially rather than comprehensively,leading to decreased cognitive activity and a diminished capacity to understand literature.To foster metaphorical thinking,the paper suggests building a text associative-semantic field focusing on metaphors.Due to its hierarchical structure,which can be envisioned as a dense nucleus surrounded by a central region of synonyms and further enveloped by a periphery of more loosely associated linguistic units,the text associative-semantic field is seen as a potent solution for facilitating improved visualization and more holistic comprehension of information,allowing students for expanding their vocabulary and strengthening associative connections.Notably,the study highlights analyzing the metaphors of emotional states as they contribute significantly to a more profound interpretation of the text,understanding the writer’s unique style,deepening the students’engagement with the book,and expanding their emotional experiences.
文摘The rapid growth of digital data necessitates advanced natural language processing(NLP)models like BERT(Bidi-rectional Encoder Representations from Transformers),known for its superior performance in text classification.However,BERT’s size and computational demands limit its practicality,especially in resource-constrained settings.This research compresses the BERT base model for Bengali emotion classification through knowledge distillation(KD),pruning,and quantization techniques.Despite Bengali being the sixth most spoken language globally,NLP research in this area is limited.Our approach addresses this gap by creating an efficient BERT-based model for Bengali text.We have explored 20 combinations for KD,quantization,and pruning,resulting in improved speedup,fewer parameters,and reduced memory size.Our best results demonstrate significant improvements in both speed and efficiency.For instance,in the case of mBERT,we achieved a 3.87×speedup and 4×compression ratio with a combination of Distil+Prune+Quant that reduced parameters from 178 to 46 M,while the memory size decreased from 711 to 178 MB.These results offer scalable solutions for NLP tasks in various languages and advance the field of model compression,making these models suitable for real-world applications in resource-limited environments.
基金funded by Science Research Project of Hebei Education Department(BJ2025238)Humanities and Social Science Research Project of Hebei Normal University(S24YX002)Humanities and Social Science Research Foundation of Hebei Normal University(S22B019).
文摘This study aimed to determine the reliability,validity and measurement invariance of scores from the Difficulties in Emotion Regulation Scale-8 in Chinese context.A total of 1114 Chinese adolescents were participants in three phases:N=424 for the initial DERS-8 measure completion;N=586 the DERS-8,General Anxiety Disorder Scale,Depression Scale and Emotion Regulation Scale completion,with an interval of one month.Then an additional 104 adolescents also completed DERS-8,General Anxiety Disorder Scale,Depression Scale and Emotion Regulation Scale.Both exploratory and confirmatory factor analyses confirmed the one-factor model of the scale,and the fitness indicators wereχ^(2)/df=4.05,RMSEA=0.07,CFI=0.98,and TLI=0.97.Each item of the DERS-8 had good discrimination.The internal consistency reliability coefficient,split-half reliability coefficient and test-retest reliability coefficient of the scale scores were 0.90,0.87 and 0.66,respectively.The findings suggest the Chinese version of the DERS-8 is a reliable measure of difficulty of emotion regulation in Chinese adolescents.
