Types Of Emotions Research Articles

Low-resource MobileBERT for emotion recognition in imbalanced text datasets mitigating challenges with limited resources.

Modern dialogue systems rely on emotion recognition in conversation (ERC) as a core element enabling empathetic and human-like interactions. However, the weak correlation between emotions and semantics poses significant challenges to emotion recognition in dialogue. Semantically similar utterances can express different types of emotions, depending on the context or speaker. In order to tackle this challenge, our paper proposes a novel loss called Focal Weighted Loss (FWL) with adversarial training and the compact language model MobileBERT. Our proposed loss function handles the problem of imbalanced emotion classification through Focal Weighted Loss and adversarial training and does not require large batch sizes or more computational resources. Our approach has been employed on four text emotion recognition benchmark datasets, MELD, EmoryNLP, DailyDialog and IEMOCAP demonstrating competitive performance. Extensive experiments on these benchmark datasets validate the effectiveness of our proposed FWL with adversarial training. This enables more human-like interactions on digital platforms. Our approach shows its potential to deliver competitive performance under limited resource constraints, comparable to large language models.

Mathematics achievement emotions: Global trend, emotional treatment, and directions for future research

Background: The development of studies related to achievement emotions in mathematics learning has been increasingly grown in two last decades. Achievement emotions is one of significant predictors for students’ mathematics achievement. Nevertheless, to date no publications have been found that particularly review studies regarding mathematics achievement emotions.Aim: Present study highlights global trend of studies in mathematics achievement emotion for future research and examines the effect of emotional treatment on achievement emotions in mathematics across treatment type, treatment duration, and emotional type.Method: A systematic review using bibliometric analysis and meta-analysis was applied to do this study in which 223 documents from Scopus database published in the period of 2004 – 2023 were used as the data. To analyze the data, this study was promoted by some software, such as PoP, VOSviewer, and CMA.Result: Results revealed that global trends of studies regarding mathematics achievement emotions describe that number of publications slightly increased while number of citations relatively fluctuated from 2004 to 2023. There were several main themes which emerged in two last decades related to mathematics achievement emotions, such as emotional type, emotional treatment, activities-and outcomes-related emotion, mathematics content, and factors-related emotion. Moreover, emotional treatments slightly increased students’ positive emotions and decreased students’ negative emotions.Conclusion: This implies that the stability of mathematics achievement emotions of students in doing mathematics activities has to be generated to promote students’ mathematics achievement in which a few of emotional treatments, such as psychological therapies and web-based learning can be applied to stabilize students’ mathematics achievement emotions.

To believe or not to believe: leader’s belief about emotion usefulness and its impact on team dynamics

BackgroundThis study aims to investigate the impact of a leader’s beliefs in the usefulness of emotions on the emotional competence and relationship conflicts of their teams.MethodsThe data were collected through an online survey targeting leaders with at least three years of experience in managerial positions in South Korean workplaces, with a total of 326 participants. Latent Profile Analysis (LPA) was conducted to classify leaders into latent groups based on their beliefs regarding the usefulness of positive and negative emotions.ResultsThe latent profile analysis of the leader’s beliefs in the usefulness of positive and negative emotions identified four groups: High Usefulness (HU) Group, High Positive Usefulness (HPU) Group, Reference Group for comparison, and Low Usefulness (LU) Group. It was found that both the HU Group and the HPU Group, who perceive the usefulness of both types of emotions and positive emotions, respectively, showed higher levels of emotional repair and lower levels of relationship conflict within the team compared to the Reference Group and the LU Group.ConclusionsThis study not only fills a gap in organizational research by establishing a clear link between leaders’ emotional beliefs and team dynamics but also emphasizes the social influence of leaders’ emotions within the team setting. The findings of this research advocate for a strategic update to leadership development programs, suggesting the integration of elements specifically designed to augment leaders’ understanding and management of emotional dynamics within their teams.

Stigma associated with dementia among recreation and leisure studies students and professionals

ABSTRACT Stigma negatively impacts quality of life of people living with dementia and their families and their interactions with others (e.g. community members, health and social care professionals). While recreation and leisure studies professionals play a key role in challenging this stigma by facilitating the engagement of persons living with dementia in meaningful activities in their communities, to date no study has explored stigma associated with dementia in the recreation and leisure studies sector. With an interest in addressing this gap, we conducted an international online survey study with 174 individuals to explore their beliefs, attitudes and behavioural intentions regarding persons living with dementia. We found that while both students and professionals demonstrated cognitive, emotional and behavioural types of stigma towards persons living with dementia, students had higher levels of stigma than professionals. Given the growing prevalence of dementia and increasing calls for more inclusive recreation and leisure services, our findings demonstrate the need for further research to inform the development of innovative approaches to addressing stigma in this sector.

과학교육전공생들의 사범대학 적응과정에서 나타나는 ((예비교사))*의 수용과 저항: Lacan 정신분석학의 상징계 이론을 토대로

Objectives This study assumed that the career conflict that appears during the settlement process of students majoring in science education at a teacher's college can start with the process of defining the student subject as a “pre-service teacher” and reinterpreted this with the signifier theory of Lacanian psychoanalysis. Methods For the study, 60 third- and fourth-year science education students from three national universities across the country participated, and the data were analyzed through word cloud and language network analysis and qualitative analysis. Results As a result of the study, it was found that current students define themselves as ((pre-service teachers)) in terms of their definition and personality and internalize this, especially in terms of personality. In addition, professors played a major role in the signification of ((pre-service teacher)), and signification was taking place in the overall curriculum of the College of Education. Lastly, the type of emotion toward ((pre-service teacher)), the perception of whether ((pre-service teacher)) reflects one's own identity, and the accepting attitude toward ((pre-service teacher)) were closely related to each other. Conclusions Accordingly, this study suggested that ((prospective teachers)) can be one of the factors that can cause conflict or career settlement in the teaching profession and suggested attempting a new psychoanalytical approach to the problem of career conflict in teachers' colleges.

EXPRESS: Facial Occlusion with Medical Masks: Impacts on Emotion Recognition Rates for Emotion Types and Intensities.

During the COVID-19 pandemic, mask-wearing became prominent or required worldwide as a predominant preventative strategy up until and even after vaccines became widely available. Because masks make emotion recognition more challenging for both the face and voice, medical and behavioral/mental health providers became aware of the disruptions this generated in practitioner-patient relationships. The current set of studies utilized two adult samples, first from United States college students (N = 516) and second from the U.S. American general public (N = 115), to document the severity and types of errors in facial expression recognition that were exacerbated by medical mask occlusion. Using a within-subjects experimental design and a well-validated test of emotion recognition that incorporated multi-ethnic adult facial stimuli, both studies found that happy, sad, and angry faces were significantly more difficult to interpret with masks than without, with lesser effects for fear. Both high- and low-intensity emotions were more difficult to interpret with masks, with a greater relative change for high-intensity emotions. The implications of these findings for medical and behavioral/mental health practitioners are briefly described, with emphasis on strategies that can be taken to mitigate the impact in healthcare settings.

The causal relationship between negative emotions and inflammatory dermatoses: a bidirectional Mendelian randomization study.

Observational studies have suggested a potential link between emotions and inflammatory dermatoses. However, research on the causal relationship between different types of emotions and inflammatory dermatoses is lacking. This study is aimed to investigate the causal relationship between negative emotions and inflammatory dermatoses through Mendelian randomization (MR) analysis. Summary data of seven negative emotions were obtained from a genome-wide association study (GWAS) conducted by the MRC-IEU consortium. Seven inflammatory dermatoses including vitiligo, psoriasis, systemic lupus erythematosus, eczema, atopic dermatitis, acne, and rosacea were obtained from published GWAS. The MR analysis primarily employed the Inverse variance weighted (IVW) method, and supplemented by MR-Egger and other three MR methods. The IVW method revealed that guilty feelings have potential to increase the risk of psoriasis (OR = 1.02, 95% CI: 1.00-1.05, P = 0.019), while worrier/anxious feelings have a potential risk effect on eczema (OR = 1.07, 95% CI: 1.00-1.13, P = 0.042). Psoriasis could increase the occurrence of miserableness (OR = 1.41, 95% CI: 1.18-1.68, P = 0.0001), worrier/anxious feelings (OR = 1.26, 95% CI: 1.02-1.57, P = 0.033), nervous feelings (OR = 1.25, 95% CI: 1.05-1.49, P = 0.012), and loneliness/isolation (OR = 1.19, 95% CI: 1.04-1.36, P = 0.009). Eczema might cause an increased incidence of worrier/anxious feelings (OR = 1.038, 95% CI: 1.007-1.070, P = 0.014). This MR study revealed bidirectional causality between worrier/anxious feelings and eczema. It also found that guilty feelings may elevate the risk of psoriasis, and individuals with psoriasis may experience increased rates of miserableness, worrier/anxious feelings, nervous feelings, and loneliness/isolation.

Unraveling the distinct ambiguities of happiness and fear: neurodynamic and machine learning perspectives

ABSTRACT Using a public database, the research combined event-related potentials (ERP), time-frequency analysis (TFR) and machine learning to compare brain activities during Confusion and Unconfusion states. The findings revealed that processing ambiguous emotions decreased LPP amplitude compared to the Unconfusion state, supporting LPP as a biomarker for emotional ambiguity. Additionally, fear-related ambiguity showed greater beta wave power than happiness, indicating heightened brain sensitivity to threats. Machine learning analysis further demonstrated that fear-related features were more critical in distinguishing emotional ambiguity than happiness, corroborating non-phase-locked signal results. These results show that emotion types, particularly fear, significantly modulate brain activity in processing emotional ambiguity, highlighting increased sensitivity and adaptability to fear-related ambiguity. This research enhances our understanding of cognitive processing in emotional ambiguity and offers insights into the neurobiological basis and therapeutic strategies for emotional disorders.

Implementation of Text Mining to Detect Emotions of Fuel Price Increase Using BERT-LSTM Method

Fuel is crucial for everyday life, especially as a primary source of transportation fueled by oil. In early April 2022, Indonesia experienced a significant event that deeply affected its populace: a surge in fuel prices. Addressing this pressing issue, this study employs emotion classification utilizing BERT and LSTM methods on social media data, particularly from platforms like YouTube, to categorize emotional responses to governmental decisions. This research aims to classify social media discourse surrounding fuel-related topics, notably the increases in fuel prices. The highest accuracy, at 95%, was achieved with oversampling techniques, contrasting with a mere 47% accuracy without oversampling. Surprisingly, experiments indicate that employing oversampling and BERT for emotion classification results in reduced accuracy during testing phases.

Z세대의 동료에 대한 주관성 연구: 국내 EAP기업을 중심으로

This study focused on domestic EAP companies to understand the types of perceptions of peers of Generation Z and their characteristics in depth. To this end, by applying the Q methodology, Q sorting was conducted on 40 Q samples of 20 Gen Z (9 males and 11 females) of domestic EAP companies using the forced classification method, and the subjectivity perception of peers was explored using the QUANL program. As a result of the study, perceptions of colleagues were derived into four types: “work cooperation type”, “emotional stability type”, “growth support type”, and “public relationship type”. This study is meaningful in that it categorized and analyzed the subjectivity of Gen Z's peers, and it is expected that it can be used as basic data for education and organizational culture development using peers.

Exploring unobserved heterogeneity of speech fluency and its dynamic interactions with emotions

Abstract The present study utilized a parallel-process growth mixture modeling technique to investigate the heterogeneity in the development of speech fluency at the (sub)group level, and to explore the interrelationships between speech fluency and different types of emotions among 126 Chinese EFL learners for four months. The study identified salient patterns emergent out of the developmental process of speech fluency, with two developmental patterns for speech rate and two for mean length of run respectively. Interaction dynamics between speech fluency and different emotions were also revealed, with anxiety and enjoyment both negatively affecting the development of L2 speech fluency over time. This study shows that parallel-process growth mixture modeling is an efficient method for identifying the heterogeneity of language development within a larger population and for exploring dynamic relations over time.

The Influence of Negative Affect and Food Stimuli on Cognitive Flexibility in Adolescents With Anorexia Nervosa.

Inflexible thinking among individuals with anorexia nervosa (AN) was proposed to reflect difficulties in set-shifting. However, studies assessing set-shifting in AN often find mixed results, especially in adolescent samples. It has been proposed that affective states and exposure to disorder-salient stimuli may modulate executive functions in AN. The current study examined the influence of induced negative emotion on the ability to shift toward or away from a food categorisation task among adolescents with AN. The study included 47 adolescents with AN and 41 healthy adolescents who performed a modified task-switching paradigm. No indication of general set-shifting difficulties among adolescents with AN was found. Nevertheless, the results showed that when negative emotion was induced, adolescents with AN shifted from a non-food categorisation task to a food categorisation task with greater efficiency compared to a neutral emotion condition. Emotion and switch type did not influence set-shifting abilities among healthy adolescents. The findings indicate automatic and more efficient switching towards preoccupation with food among adolescents with AN while experiencing negative emotion. The results emphasise the important role played by situational factors in modulating cognitive abilities in individuals with AN.

“Do I know how you feel?” Parents’ and adolescents’ recognition of each other’s daily moods

The study tested daily mutual emotion recognition in 153 parent-adolescent triads, adolescents’ mean age, 15.71 years ( SD = 1.53), 51% girls. Over seven consecutive days, adolescents and parents provided self and other reports on daily positive mood, daily negative mood (distress, anger), and daily time spent together. A series of analyses of variance showed parents underestimated adolescents’ positive and negative moods, while adolescents overestimated parents’ negative moods and underestimated positive ones. Multilevel path analysis showed mothers recognized adolescents’ negative and positive daily moods, while fathers only recognized adolescents’ positive mood. Adolescents recognized changes in their parents’ daily moods, but not always the emotion type. All significant daily associations were modest. Overall, it seems parents and adolescents are not well-informed on each other’s affective changes.

The Modulatory Effect of Exogenous Orienting on Audiovisual Emotional Integration: An ERP Study.

In this study, we explored the interplay between exogenous orienting attention and emotional audiovisual integration (AVI) via electroencephalography (EEG). We designed a 2 (cue validity: valid, invalid) × 3 (emotion types: happiness, neutral and sadness) × 3 (modality: visual, auditory, audiovisual) discrimination task on the basis of the cue-target paradigm. Twenty-two participants (average age: 21.71 ± 1.84 years; 13 females, 9 males) were enrolled in this experiment. Participants were asked to respond to three emotional stimuli presented in different modalities by pressing a corresponding key. The results indicated faster responses to multisensory stimuli than to unisensory stimuli and to the valid cue condition than to the invalid cue condition, which indicated multisensory advantage and cueing effect occurred. In addition, happiness stimuli induced the fastest response compared with neutral and sadness emotion stimuli. EEG findings indicated a reduction in audiovisual integration induced by valid exogenous orienting in the frontal, central and parietal lobe regions. Moreover, neutral emotional stimuli elicited greater audiovisual integration than stimuli expressing happiness and sadness did. Overall, valid exogenous cues and emotional processing decreased audiovisual integration. The present study sheds light on how exogenous attention modulates emotional audiovisual integration and highlights the complex interactions among attention, sensory processing, and the emotional context in multisensory perception.

The influence of physical exercise on negative emotions in adolescents: a meta-analysis.

Adolescence is also accompanied by ongoing mood changes (relative to childhood and adulthood), which can trigger more extreme negative emotional responses. Physical exercise alleviates negative emotions and reduces the risk of mental illness. However, the effect of physical exercise on negative emotions in adolescents is unclear, so it is valuable to synthesize previous studies with meta-analysis. To examine the influence of physical exercise (PE) intervention on negative emotions in adolescents aged 10 to 19 years. We retrieved the articles from PubMed, Web of Science, EBSCO, Cochrane, and Embase up to April 11, 2024. The main search terms were physical exercise, negative emotions, adolescents, randomized controlled trials. The meta-analysis was conducted using Review Manager 5.3. A random-effects model was employed to calculate the standardized mean difference (SMD) and 95% confidence interval (CI). Subgroups were analysed as the type of negative emotions, type of control group, intervention type, duration, time, frequency. The PE intervention group exhibited a significantly superior improvement in alleviating negative emotions compared to the control group (SMD = -0.59, 95% CI: -0.92 to -0.26, p < 0.01, Z = 3.50, I² = 95%). PE was particularly effective in mitigating adolescent depression (SMD = -0.67, 95% CI = -1.07 to -0.28, p < 0.01, I² = 96%) but did not yield significant results in reducing adolescent anxiety (SMD = -0.29, 95% CI = -0.63 to 0.05, p = 0.10, I² = 95%). PE intervention can ameliorate negative emotions in adolescents. https://www.crd.york.ac.uk/prospero/, identifier CRD42024534375.

EXPLOITING OPTIMAL SELF-ATTENTION DEEP LEARNING-BASED RECOGNITION OF TEXTUAL EMOTIONS FOR DISABLED PERSONS

A disability is a significant issue that has posed and continues to pose a challenge. Disability is a basis of frustration because it can be observed as a mental, constraint, cognitive, and physical handicap that inhibits the individual’s growth and involvement. Consequently, significant effort has been put into removing these kinds of restrictions. These initiatives address the trouble that disabled people encounter. People with disabilities often need to rely on others to meet their requirements. Machine learning (ML) is excelling in producing smart cities and offering a secure environment for disabled individuals. Emotional detection is an important research domain that can expose many appreciated inputs. Emotion is expressed differently through speech and facial expressions, gestures, and written text. Emotion detection in a text document is fundamentally a content-based classification task, utilizing models from deep learning (DL), complex systems and natural language processing (NLP). This paper presents an Optimal Self-Attention DL-based Recognition of Textual Emotions (OSADL-RTE) technique for Disabled Persons. The presented OSADL-RTE technique focuses on identifying distinct types of emotions in the textual data. As a primary preprocessing step, the OSADL-RTE technique comprises different phases to transform the input in a useful way. For word embedding, the bag of words (BoWs) approach is exploited. The OSADL-RTE technique derives self-attention long short-term memory (SA-LSTM) approach to identify emotions. Lastly, the arithmetic fractals optimization algorithm (AOA) approach correctly tunes the hyperparameter selection of the SA-LSTM approach. The experimental study of the OSADL-RTE approach occurs on the emotion database. The investigational outcome of the OSADL-RTE approach portrayed a superior accuracy outcome of 99.59% over existing methods.

How the workplace usage of AI in China influences proactive behaviour? The role of pride and shame

ABSTRACT Based on the cognitive appraisal theory of emotions, we investigated the impact of AI usage on individuals’ positive and negative emotions as well as their proactive behaviour. Through a survey study conducted in China among 203 employees who have work experiences with AI with a one-month interval, we revealed the influence pathway between AI usage and proactive behaviour, which is mediated by two types of self-conscious emotions: pride and shame, and the satisfaction of competence need can moderate the relationship between AI usage and pride. The theoretical and implications of this study were discussed.

PBL 교육과정에서 학습자의 성취 수준에 따른 학습몰입 특성: 성찰일지의 코퍼스 기반 분석

Objectives The study aims to analyze the learning engagement characteristics based on learners' achievement levels in a Project-Based Learning (PBL) curriculum. Through a corpus-based analysis of reflective journals, the research seeks to objectively evaluate and differentiate the emotional, behavioral, and cognitive engagement types of learners. Methods This research employed a corpus-based linguistic approach to analyze the reflective journals of learners from a PBL course. A total of 24 students from C University participated, divided into high-achieving and low-ach-ieving groups. The reflective journals, collected over nine weeks, were analyzed using the AntConc program to ex-tract keywords representing emotional, behavioral, and cognitive engagement. Statistical analyses, including One-Way ANOVA and independent samples t-test, were conducted to determine the differences in engagement types within and between the groups. Results The analysis revealed distinct differences in engagement characteristics between high-achieving and low-achieving learners. High-achieving learners exhibited higher levels of emotional, behavioral, and cognitive engagement, reflected in a greater frequency of keywords related to these dimensions. The differences were statistically significant, highlighting the need for differentiated instructional strategies to cater to varying learner needs. Conclusions The findings emphasize the importance of tailoring educational strategies to the individual needs of learners based on their engagement patterns. This approach can enhance the effectiveness of PBL by fostering deeper and more meaningful learning experiences. The study contributes to the development of targeted teaching methods that support both high-achieving and low-achieving students, ultimately improving overall learning outcomes.

EMOTION RECOGNITION IN LEARNERS WITH EMOJI SENTIMENT ACCOMPANIMENT USING THE PHOBERT MODEL

This paper proposes an advanced method for recognizing learners' emotions by incorporating the use of emojis to reflect the modern communication tendencies of learners, typically young individuals. The method is built on the PhoBERT model, a variant of BERT optimized for Vietnamese. Data was collected from opinion surveys of learners at the Ho Chi Minh City campus of the University of Transport and Communications to train and test the model. The system is designed to analyze text and recognize seven basic emotions: enjoyment, trust, hope, sadness, surprise, fear, and others. Corresponding emojis are then assigned to each emotion type to more clearly illustrate the learners' emotional states. Experimental results show that combining PhoBERT and emojis not only enhances the accuracy of emotion recognition but also makes communication more intuitive and vivid. The model achieved an accuracy of 74.1%. The paper also discusses practical applications of this system in the field of education, where teachers can quickly and accurately understand and respond to students' emotions, thereby improving teaching effectiveness.

The perception of emotional prosody in Mandarin Chinese words and sentences

Emotional prosody refers to the ways in which the tone of voice can be modulated to convey emotions, feelings, and attitudes. Previous studies have explored the perception of emotional prosody and whether native speakers (L1) have an in-group advantage in recognizing the emotional prosody of their own cultural groups over non-native speakers. However, little is known about whether these findings in non-tonal languages can be generalized to tonal languages. Mandarin Chinese uses the tone of voice to encode word meanings in addition to emotional prosody. This study investigates the perception of emotional prosody in Mandarin Chinese using an emotion judgment task, focusing on the effects of emotion type (e.g., neutral, joy, anger, sadness) and syllable length (e.g., monosyllable, disyllable, trisyllable, and sentence). Three groups were included, consisting of 20 native Chinese speakers (native group), 20 L1-English L2-Chinese learners (second language group), and 20 native English speakers without Chinese learning experience (non-native group). The results revealed that all three groups can identify emotional prosody well above the chance level in Mandarin Chinese words and sentences. Moreover, the native group and the second language (L2) group showed an in-group advantage in recognizing emotional prosody compared to the non-native group, highlighting the impact of linguistic experience in addition to cultural backgrounds on the perception of emotional prosody. Notably, the effects of emotion type and syllable length differed across the three groups in terms of their perception of emotional prosody. The native group had difficulty identifying positive emotional prosody, whereas both the L2 group and the non-native group showed a pattern of improved accuracy as syllable length increased, with an interaction effect with emotion type.