Search Results (15,353)

With the rapid development of live streaming e-commerce, green agricultural products have become an important consumer category. However, sales still face challenges such as weak brand effects, content homogeneity, and the lack of professional hosts. Research shows that various factors influence consumers’ purchase intentions, with design-driven attributes and brand image playing crucial roles. However, their impact in the context of green agricultural product live streaming remains underexplored. This study, based on the S-O-R theory, investigates the factors that stimulate consumer purchase intentions for green agricultural products and reveals the influence of design-driven attributes on purchase intentions. A total of 472 valid responses were collected through a questionnaire. The results indicate that social presence and brand image have a positive impact on purchase intention, with green perceived value and emotional attitude acting as full mediators. However, design-driven attributes do not have a significant direct impact on purchase intention. Nevertheless, emotional attitude plays a significant mediating role between design-driven attributes and purchase intention. This study contributes to the research on consumer behavior and perceived value in live streaming environments, particularly emphasizing the importance of design-driven attributes, and provides insights for optimizing live streaming strategies and improving agricultural product design. Full article

Background: Family breakdown, separation, and divorce (FBSD) are often traumatic events, particularly for fathers who face unique challenges. These include emotional, psychological, and financial struggles, often exacerbated by abusive behaviours from ex-partners. This study explores fathers’ experiences of FBSD, focusing on both the breakdown event itself and any abuse, including coercive control and parental alienation, before and after the separation. Methods: A mixed-methods approach was employed, including a survey of 141 men and follow-up interviews with 30 participants. Data were analysed using reflexive thematic analysis to identify key themes related to FBSD and associated abuse. Results: Fathers reported significant emotional, psychological, and financial distress, with many experiencing ongoing abuse and coercive control after separation. Abuse often continued through legal processes and manipulation of child access. Parental alienation emerged as a prominent form of post-separation abuse, with fathers describing attempts by ex-partners to undermine their relationships with their children. Conclusions: The findings highlight the need for gender-inclusive services that address the specific challenges fathers face during and after FBSD, particularly in relation to post-separation abuse. Targeted interventions are necessary to support fathers’ well-being and ensure their continued involvement in their children’s lives. Full article

Multimodal sentiment analysis faces a number of challenges, including modality missing, modality heterogeneity gap, incomplete datasets, etc. Previous studies usually adopt schemes like meta-learning or multi-layer structures. Nevertheless, these methods lack interpretability for the interaction between modalities. In this paper, we constructed a new dataset, SM-MSD, for sentiment analysis in social media (SAS) that differs significantly from conventional corpora, comprising 10K instances of diverse data from Twitter, encompassing text, emoticons, emojis, and text embedded in images. This dataset aims to reflect authentic social scenarios and various emotional expressions, and provides a meaningful and challenging evaluation benchmark for multimodal sentiment analysis in specific contexts. Furthermore, we propose a multi-task framework based on heterogeneous graph neural networks (H-GNNs) and contrastive learning. For the first time, heterogeneous graph neural networks are applied to multimodal sentiment analysis tasks. In the case of additional labeling data, it guides the emotion prediction of the missing mode. We conduct extensive experiments on multiple datasets to verify the effectiveness of the proposed scheme. Experimental results demonstrate that our proposed scheme surpasses state-of-the-art methods by 1.7% and 0 in accuracy and 1.54% and 4.9% in F1-score on the MOSI and MOSEI datasets, respectively, and exhibits robustness to modality missing scenarios. Full article

Many people with BPD (borderline personality disorder) experience emotional dysregulation and thus engage in NSSI (non-suicidal self-injury), potentially in the pursuit of emotional regulation. However, research is lacking on whether body modifications (piercings, tattoos, etc.) are linked to BPD in a similar way to NSSI. In the current study, we hypothesized (1) that body modifications are associated with BPD symptoms, (2) that emotional regulation and self-expression motivations for body modifications specifically account for variance in BPD symptoms, and (3) that NSSI craving correlates with body modification craving. Participants (N = 199, ages 18–67, located in the USA) were surveyed on BPD symptomatology, NSSI craving, emotional regulation abilities, and the presence of body modifications. The extent of tattooing (number of tattoos and percentage of body surface covered) was not significantly associated with BPD symptomatology, but the number of piercings was. Individuals with higher BPD symptomatology were not more likely to report emotional regulation and self-expression as motivations for obtaining body modifications. NSSI craving scores were significantly positively correlated with body modification craving scores. Body modification may be an alternative method of emotional regulation to NSSI in individuals with BPD, which clinicians may want to consider when treating those with BPD and NSSI. Full article

Qualitative data analysis (QDA) tools are essential for extracting insights from complex datasets. This study investigates researchers’ perceptions of the usability, user experience (UX), mental workload, trust, task complexity, and emotional impact of three tools: Taguette 1.4.1 (a traditional QDA tool), ChatGPT (GPT-4, December 2023 version), and Gemini (formerly Google Bard, December 2023 version). Participants (N = 85), Master’s students from the Faculty of Electrical Engineering and Computer Science with prior experience in UX evaluations and familiarity with AI-based chatbots, performed sentiment analysis and data annotation tasks using these tools, enabling a comparative evaluation. The results show that AI tools were associated with lower cognitive effort and more positive emotional responses compared to Taguette, which caused higher frustration and workload, especially during cognitively demanding tasks. Among the tools, ChatGPT achieved the highest usability score (SUS = 79.03) and was rated positively for emotional engagement. Trust levels varied, with Taguette preferred for task accuracy and ChatGPT rated highest in user confidence. Despite these differences, all tools performed consistently in identifying qualitative patterns. These findings suggest that AI-driven tools can enhance researchers’ experiences in QDA while emphasizing the need to align tool selection with specific tasks and user preferences. Full article

Aboriginal and Torres Strait Islander (hereafter, respectfully, Indigenous) men’s health and social indicators reflect an ongoing legacy of social disruption with profound implications for broader family and community contexts. In response to recognized needs, healing programs have been implemented within Australia. The literature on relevant best practices for Indigenous men’s healing was explored to inform the planning and implementation of a local program. A scoping review of electronic databases was undertaken to retrieve information between 2012 and 2022 on social and emotional healing programs for Indigenous men that included a program evaluation. Of the 2123 identified articles, many lacked a program evaluation or were not specific to male participants, with nine meeting the inclusion criteria for the review. Six central elements that supported the programs’ reported efficacy were identified: kinship, cultural understanding, a view of healing as being holistic, a strengths-based approach, a male leadership team, and a consistent meeting space. These elements were important for the social and emotional healing of the Indigenous male participants. Based on these findings, there is an increased need for the identified elements to be incorporated into programs for Indigenous men to accompany ongoing efforts in improving the wellbeing of the Indigenous population overall. Full article

This paper introduces a novel joint model architecture for Speech Emotion Recognition (SER) that integrates both discrete and dimensional emotional representations, allowing for the simultaneous training of classification and regression tasks to improve the comprehensiveness and interpretability of emotion recognition. By employing a joint loss function that combines categorical and regression losses, the model ensures balanced optimization across tasks, with experiments exploring various weighting schemes using a tunable parameter to adjust task importance. Two adaptive weight balancing schemes, Dynamic Weighting and Joint Weighting, further enhance performance by dynamically adjusting task weights based on optimization progress and ensuring balanced emotion representation during backpropagation. The architecture employs parallel feature extraction through independent encoders, designed to capture unique features from multiple modalities, including Mel-frequency Cepstral Coefficients (MFCC), Short-term Features (STF), Mel-spectrograms, and raw audio signals. Additionally, pre-trained models such as Wav2Vec 2.0 and HuBERT are integrated to leverage their robust latent features. The inclusion of self-attention and co-attention mechanisms allows the model to capture relationships between input modalities and interdependencies among features, further improving its interpretability and integration capabilities. Experiments conducted on the IEMOCAP dataset using a leave-one-subject-out approach demonstrate the model’s effectiveness, with results showing a 1–2% accuracy improvement over classification-only models. The optimal configuration, incorporating the joint architecture, dynamic weighting, and parallel processing of multimodal features, achieves a weighted accuracy of 72.66%, an unweighted accuracy of 73.22%, and a mean Concordance Correlation Coefficient (CCC) of 0.3717. These results validate the effectiveness of the proposed joint model architecture and adaptive balancing weight schemes in improving SER performance. Full article

The development of emotionally intelligent computers depends on emotion recognition based on richer multimodal inputs, such as text, speech, and visual cues, as multiple modalities complement one another. The effectiveness of complex relationships between modalities for emotion recognition has been demonstrated, but these relationships are still largely unexplored. Various fusion mechanisms using simply concatenated information have been the mainstay of previous research in learning multimodal representations for emotion classification, rather than fully utilizing the benefits of deep learning. In this paper, a unique deep multimodal emotion model is proposed, which uses the meaningful neural network to learn meaningful multimodal representations while classifying data. Specifically, the proposed model concatenates multimodality inputs using a graph convolutional network to extract acoustic modality, a capsule network to generate the textual modality, and vision transformer to acquire the visual modality. Despite the effectiveness of MNN, we have used it as a methodological innovation that will be fed with the previously generated vector parameters to produce better predictive results. Our suggested approach for more accurate multimodal emotion recognition has been shown through extensive examinations, producing state-of-the-art results with accuracies of 69% and 56% on two public datasets, MELD and MOSEI, respectively. Full article

Background: Human emotions are subjective psychophysiological processes that play an important role in the daily interactions of human life. Emotions often do not manifest themselves in isolation; people can experience a mixture of them and may not express them in a visible or perceptible way; Methods: This study seeks to uncover EEG patterns linked to emotions, as well as to examine brain activity across emotional states and optimise machine learning techniques for accurate emotion classification. For these purposes, the DEAP dataset was used to comprehensively analyse electroencephalogram (EEG) data and understand how emotional patterns can be observed. Machine learning algorithms, such as SVM, MLP, and RF, were implemented to predict valence and arousal classifications for different combinations of frequency bands and brain regions; Results: The analysis reaffirms the value of EEG as a tool for objective emotion detection, demonstrating its potential in both clinical and technological contexts. By highlighting the benefits of using fewer electrodes, this study emphasises the feasibility of creating more accessible and user-friendly emotion recognition systems; Conclusions: Further improvements in feature extraction and model generalisation are necessary for clinical applications. This study highlights not only the potential of emotion classification to develop biomedical applications, but also to enhance human–machine interaction systems. Full article

Background/Objectives: The study examined the relationships between specific Theory-of-Mind (ToM) dimensions, cognitive planning, and sleep duration in aging adults. Methods: The sample included 179 participants, comprising 46 cognitively healthy individuals, 75 diagnosed with amnestic Mild Cognitive Impairment (aMCI), and 58 with non-amnestic (naMCI). The mean age of the participants was 70.23 years (SD = 4.74), with a mean educational attainment of 12.35 years (SD = 3.22) and gender distribution of 53 men and 126 women. ToM assessment included tasks measuring the understanding and interpretation of non-literal speech, proverbs and metaphors, as well as an emotion-recognition test. For cognitive planning, a Tower Test was utilized. Sleep duration was measured using actigraphy. Results: We identified significant differences in various ToM tasks’ performance between the groups, particularly in non-literal speech tasks and third-order ToM stories. The HC group consistently outperformed both MCI groups in these tasks, with aMCI showing higher performance than naMCI. Mediation analysis applied to examine potential direct and indirect effects of sleep duration on ToM tasks indicated that total sleep time had significant indirect effects through cognitive planning—mainly as rule violation total score—on specific ToM aspects. Hence, besides the effects of MCI pathologies and especially of naMCI, sleep duration seems also to be associated with ToM performance in aging via specific executive functioning decrements. Conclusions: The findings underscore the social implications of ToM deficits due to MCI and/or sleep duration decrease, particularly in naMCI older adults, as they can seriously impair their social interactions. Targeted interventions could improve emotional understanding, communication, and overall quality of life. Full article

Behavioral computing based on visual cues has become increasingly important, as it can capture and annotate teachers’ and students’ classroom states on a large scale and in real time. However, there is a lack of consensus on the research status and future trends of computer vision-based classroom behavior recognition. The present study conducted a systematic literature review of 80 peer-reviewed journal articles following the Preferred Reporting Items for Systematic Assessment and Meta-Analysis (PRISMA) guidelines. Three research questions were addressed concerning goal orientation, recognition techniques, and research challenges. Results showed that: (1) computer vision-supported classroom behavior recognition focused on four categories: physical action, learning engagement, attention, and emotion. Physical actions and learning engagement have been the primary recognition targets; (2) behavioral categorizations have been defined in various ways and lack connections to instructional content and events; (3) existing studies have focused on college students, especially in a natural classical classroom; (4) deep learning was the main recognition method, and the YOLO series was applicable for multiple behavioral purposes; (5) moreover, we identified challenges in experimental design, recognition methods, practical applications, and pedagogical research in computer vision. This review will not only inform the recognition and application of computer vision to classroom behavior but also provide insights for future research. Full article

Affective computing is an emerging area of education research and has the potential to enhance educational outcomes. Despite the growing number of literature studies, there are still deficiencies and gaps in the domain of affective computing in education. In this study, we systematically review affective computing in the education domain. Methods: We queried four well-known research databases, namely the Web of Science Core Collection, IEEE Xplore, ACM Digital Library, and PubMed, using specific keywords for papers published between January 2010 and July 2023. Various relevant data items are extracted and classified based on a set of 15 extensive research questions. Following the PRISMA 2020 guidelines, a total of 175 studies were selected and reviewed in this work from among 3102 articles screened. The data show an increasing trend in publications within this domain. The most common research purpose involves designing emotion recognition/expression systems. Conventional textual questionnaires remain the most popular channels for affective measurement. Classrooms are identified as the primary research environments; the largest research sample group is university students. Learning domains are mainly associated with science, technology, engineering, and mathematics (STEM) courses. The bibliometric analysis reveals that most publications are affiliated with the USA. The studies are primarily published in journals, with the majority appearing in the Frontiers in Psychology journal. Research gaps, challenges, and potential directions for future research are explored. This review synthesizes current knowledge regarding the application of affective computing in the education sector. This knowledge is useful for future directions to help educational researchers, policymakers, and practitioners deploy affective computing technology to broaden educational practices. Full article

Sentiment analysis is a crucial component of text mining and natural language processing (NLP), involving the evaluation and classification of text data based on its emotional tone, typically categorized as positive, negative, or neutral. While significant research has focused on structured languages like English, unstructured languages, such as the Moroccan Dialect (MD), face substantial resource limitations and linguistic challenges, making effective sentiment analysis difficult. This study addresses this gap by exploring the integration of data-balancing techniques with machine learning (ML) methods, specifically investigating the impact of resampling techniques and feature extraction methods, including Term Frequency–Inverse Document Frequency (TF-IDF), Bag of Words (BOW), and N-grams. Through rigorous experimentation, we evaluate the effectiveness of these approaches in enhancing sentiment analysis accuracy for the Moroccan dialect. Our findings demonstrate that strategic resampling, combined with the TF-IDF method, significantly improves classification accuracy and robustness. We also explore the interaction between resampling strategies and feature extraction methods, revealing varying levels of effectiveness across different combinations. Notably, the Support Vector Machine (SVM) classifier, when paired with TF-IDF representation, achieves superior performance, with an accuracy of 90.24% and a precision of 90.34%. These results highlight the importance of tailored resampling techniques, appropriate feature extraction methods, and machine learning optimization in advancing sentiment analysis for under-resourced and dialect-heavy languages like the Moroccan dialect, providing a practical framework for future research and development in NLP for unstructured languages. Full article

Type 1 Diabetes (T1D) is a progressive autoimmune disease often identified in childhood or adolescence, with early stages detectable through pre-diabetic markers such as autoantibodies and subclinical beta-cell dysfunction. The identification of the pre-T1D stage is critical for preventing complications, such as diabetic ketoacidosis, and for enabling timely interventions that may alter disease progression. This review examines the multifaceted approach to managing T1D risk in adolescents and teens, emphasizing early detection, nutritional interventions, beta-cell preservation strategies, and psychosocial support. Screening for T1D-associated autoantibodies offers predictive insight into disease risk, particularly when combined with education and family resources that promote lifestyle adjustments. Although nutritional interventions alone are not capable of preventing T1D, certain lifestyle interventions, such as weight management and specific nutritional choices, have shown the potential to preserve insulin sensitivity, reduce inflammation, and mitigate metabolic strain. Pharmacological strategies, including immune-modulating drugs like teplizumab, alongside emerging regenerative and cell-based therapies, offer the potential to delay disease onset by protecting beta-cell function. The social and psychological impacts of a T1D risk diagnosis are also significant, affecting adolescents’ quality of life, family dynamics, and mental health. Supportive interventions, including counseling, cognitive-behavioral therapy (CBT), and group support, are recommended for managing the emotional burden of pre-diabetes. Future directions call for integrating universal or targeted screening programs within schools or primary care, advancing research into nutrition and psychosocial support, and promoting policies that enhance access to preventive resources. Advocacy for the insurance coverage of screening, nutritional counseling, and mental health services is also crucial to support families in managing T1D risk. By addressing these areas, healthcare systems can promote early intervention, improve beta-cell preservation, and support the overall well-being of adolescents at risk of T1D. Full article

Background/Objectives: Dementia leads to cognitive decline, affecting memory, reasoning, and daily activities, often requiring full-time care. Multisensory stimulation (MSS), combined with cognitive tasks, can slow this decline, improving mood, communication, and overall quality of life. This systematic review aims to explore methods that utilize MSS in the rehabilitation of patients with dementia. Its clinical value is rooted in its ability to offer a deep comprehension of how MSS can be successfully incorporated into rehabilitation treatments. Methods: Studies were identified from an online search of PubMed, EBSCOhost, Cochrane Library, Web of Science, Embase, and Scopus databases with a search time frame from 2014 to 2024. This review has been registered on Open OSF (n) 3KUQX. Results: Pilot studies investigating MSS interventions, encompassing Cognitive Stimulation Therapy (CST), Sonas therapy, and combined physical–cognitive exercise programs, have yielded mixed findings in individuals with dementia. CST has demonstrated significant improvements in general cognitive function, particularly in language skills, offering a promising approach for cognitive enhancement. Sonas therapy, while showing positive trends in some studies, does not consistently achieve statistically significant outcomes across all cognitive domains. Conversely, combined exercise programs have shown efficacy in improving dual-task performance, suggesting benefits for motor–cognitive integration. MSS delivered within specialized environments like Snoezelen rooms consistently produces positive effects on mood, reducing agitation and promoting relaxation. Conclusions: This review emphasizes how MSS can enhance cognitive, emotional, and behavioral results for individuals with dementia. It is essential for future research to standardize protocols, incorporate advanced technologies such as virtual reality, and rectify diversity gaps. Collaboration between different fields will improve the effectiveness and usefulness of MSS in caring for individuals with dementia. Full article