IEEE Transactions on Computational Social Systems最新文献

{"title":"Dynamic Graph Convolutional Network With Spatiotemporal and Multiscale Feature Fusion for Multistep Traffic Flow Prediction","authors":"Youcai Cheng;Shumei Bao;Yuhao Ke;Jiaxin Chen;Mengyang Liu","doi":"10.1109/TCSS.2025.3626644","DOIUrl":"https://doi.org/10.1109/TCSS.2025.3626644","url":null,"abstract":"Accurate multistep traffic flow prediction is crucial for intelligent transportation systems (ITS). Existing graph convolutional networks (GCNs) still have limitations. They struggle to capture the complex dynamic relationships between adjacent nodes in road networks, to model long-term dependencies, and fully mine cross-layer feature expressions. These limitations make long-term predictions challenging. To address these challenges, we propose a GCN based on dynamic spatiotemporal and multiscale feature fusion (DGCN-STMSF). The model adopts a shared and independent stacked architecture, taking into account cross-layer feature sharing and personalized modeling, this architecture enables better characterization of the complex dynamic relationships between nodes. We introduce an exponential smoothing attention mechanism (ESA). It embeds the exponential decay mechanism into graph-structured temporal modeling. This improves the unique feature representation between layers and enhances temporal stability and trend perception. Furthermore, a fine-grained correlation enhancement module (FGCE) is proposed, featuring a dual-layer mechanism design, combined with spatial location enhancement learning (SLEL) and cross-spatial integration learning strategy (CSIL), which are used to characterize the instantaneous changes of adjacent nodes and the interactive effects between different road sections, respectively, and dynamically model complex local and global spatial dependencies. Extensive experiments on four real datasets show that the DGCN-STMSF model demonstrates superior effectiveness and performance. On various datasets, mean absolute error (MAE), root mean square error, and mean absolute percentage error are reduced by up to 2.14%, 5.34%, and 3.12%, respectively, demonstrating good generalization ability and application value.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":"13 5","pages":"6642-6655"},"PeriodicalIF":4.6,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097756","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting Government Microblog Comment Popularity: Insights From Diffusion of Innovations","authors":"Qibiao Hu;Xueyi Li;Jingrui Hou;Ping Wang;Yan Gong","doi":"10.1109/TCSS.2025.3649053","DOIUrl":"https://doi.org/10.1109/TCSS.2025.3649053","url":null,"abstract":"Government microblog comments (GMCs) play a crucial role in facilitating public opinion and governmental communication. This study explores the prediction of GMC popularity using machine learning methods, emphasizing an innovative approach that integrates diffusion of innovations theory with a hierarchical feature framework. Along with an interpretable tabular learning algorithm, the experiments demonstrate the effectiveness of this feature-framework-based method, which outperforms pretrained large language models in predicting social media comment popularity. This approach illustrates the value of combining theory-driven feature engineering with cutting-edge machine learning to predict social media engagement. Additionally, the results provide actionable insights for government agencies to monitor public opinion trends and enhance decision-making processes.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":"13 5","pages":"6432-6446"},"PeriodicalIF":4.6,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097831","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CLIP-Driver: Multimodal Fusion Method for Driver Emotion Recognition via Event-Image Temporal Alignment","authors":"Yongfu He;Yanqing He;Ruikang Wang;Haochi Zhang","doi":"10.1109/TCSS.2026.3713030","DOIUrl":"https://doi.org/10.1109/TCSS.2026.3713030","url":null,"abstract":"Single-eye micro-expression in driving scenarios can reveal the driver’s hidden emotional state, providing crucial evidence for safety monitoring. To address the issues of event–red, green, and blue (RGB) modality gap, insufficient sequence-level dynamic alignment, and redundant-event-frame interference with semantic drift during cross-modal fusion in single-eye-based driver emotion recognition, this article proposes contrastive language-image pretraining (CLIP)-Driver: a multimodal fusion method based on event-image temporal alignment. This method constructs a shared dynamic micro-expression event–image representation space by introducing the CLIP model as a semantic bridge, thereby improving the transferability and semantic coherence of multimodal features. Subsequently, a sequence-level contrastive optimization strategy is employed to capture the dynamic evolution of micro-expressions, reducing the interference of local frame-level alignment noise in temporal representation learning. Finally, a redundancy-aware mechanism combined with consistency optimization adaptively suppresses weakly discriminative event frames and maintains cross-modal semantic consistency during multimodal fusion. Experiments on the publicly available single-eye event-based emotion (SEE) and diverse single-eye event-based emotion dataset (DSEE) datasets demonstrate the effectiveness of CLIP-Driver. Specifically, on the SEE dataset, it achieves a weighted average recall (WAR) of 94.1% and an unweighted average recall (UAR) of 94.6%. On the DSEE dataset, it achieves a WAR of 84.5% and a UAR of 85.4%. These results demonstrate that CLIP-Driver significantly outperforms existing mainstream methods and validate its superior generalization ability and recognition robustness under different lighting conditions.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":"13 5","pages":"6007-6022"},"PeriodicalIF":4.6,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097011","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Handling Dual Skewness in Citywide Crime Prediction Using Personalized Graph Federated Learning","authors":"Bhumika;Philippe Lalanda;German Vega;Debasis Das","doi":"10.1109/TCSS.2025.3641377","DOIUrl":"https://doi.org/10.1109/TCSS.2025.3641377","url":null,"abstract":"The widespread deployment of sensors and recent advances in machine learning have enabled the development of predictive services in smart cities, particularly in the domain of public safety through predictive policing across different regions. Recently, training on these distributed regions is facilitated by federated learning (FL) without exposing sensitive data. However, crime data exhibit inherently complex spatiotemporal dynamics and suffer from dual skewness, as both the quantity and category distribution of crimes vary significantly across regions. Most existing federated methods struggle to effectively handle such skewed distributions, while also being limited to capture spatial dependencies. To overcome these challenges, we propose an approach called <italic>g</i>raph <italic>s</i>tructured <italic>p</i>ersonalized <italic>f</i>ederated <italic>l</i>earning (<italic>GSpfl</i>), which jointly models spatial and temporal patterns in crime data. Specifically, <italic>GSpfl</i> incorporates graph based aggregation at the server to model spatial dynamics, where similarity based adjacency matrix enable convolution among related clients to mitigate quantity skewness. On the client side, temporal dynamics are learned locally with regularization terms to balance global knowledge sharing and local model adaptation, while Focal Tversky loss is employed to address category imbalance. Experiments on real-world crime datasets from Los Angeles (LA) and Chicago (CHI) demonstrate the superior performance of our approach compared to ten baseline and state-of-the-art FL methods.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":"13 5","pages":"6469-6480"},"PeriodicalIF":4.6,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Managing Public Opinions Based on the Self-Confidence-Driven Hegselmann–Krause Model","authors":"Xia Chen;Mengting Gao;Guoyin Jiang;Qirui Li;Xuejing Yang;Yangjingjing Zhang","doi":"10.1109/TCSS.2025.3630055","DOIUrl":"https://doi.org/10.1109/TCSS.2025.3630055","url":null,"abstract":"Public opinion management plays a vital role in both government governance and corporate competition. Opinion dynamics provides a key framework for its study, with the classic Hegselmann–Krause (HK) model using confidence thresholds to define individuals’ opinion exploration and interaction ranges. However, many existing studies treat these thresholds as exogenous, overlooking the influence of internal psychological traits—particularly self-confidence—on external exploratory behavior. To bridge this gap, we propose a self-confidence-driven HK (SCD-HK) model by establishing a driving relationship between individuals’ internal self-confidence levels and their external confidence thresholds. Based on this, we develop an optimal intervention model under time constraints to guide public opinion evolution. Numerical analyses, including sensitivity tests, comparative experiments, and a case study, reveal that: 1) moderate self-confidence levels better promote consensus than extreme values; 2) a concave relationship between self-confidence and confidence thresholds better facilitates consensus; and 3) our SCD-HK model outperforms traditional models in consensus ratio, convergence speed, and intervention cost. This article highlights the importance of incorporating the relationship between individuals’ inherent self-confidence levels and external confidence thresholds in opinion evolution, and our findings offer practical insights for more effective opinion management.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":"13 5","pages":"6532-6546"},"PeriodicalIF":4.6,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097175","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CARD: Contactless Affect Recognition Database Using Young Adults of Premier Indian University","authors":"Satarupa Uttarkabat;Satyajit Nayak;Aurobinda Routray;Priyadarshi Patnaik","doi":"10.1109/TCSS.2026.3701521","DOIUrl":"https://doi.org/10.1109/TCSS.2026.3701521","url":null,"abstract":"Emotional distress and declining psychological well-being are increasingly prevalent among student populations in India, emerging as a significant concern relative to other societal segments. In the context of computational social systems, especially within human–device interaction (HDI) and social media–mediated communication, addressing these mental health (MH) challenges demands a nuanced understanding of affective states through both verbal expression and subtle nonverbal behavior. This creates technical and methodological obstacles for nonintrusive HDI systems, including the need to simulate naturalistic interaction settings, capture various social signals, decode authentic emotional responses, and ensure high fidelity in emotion recognition without relying on obtrusive sensing technologies. This study aimed to assess the emotional well-being of young adults in premier Indian institutions through various technological interventions during machine interactions. However, the lack of standardized noncontact databases has hindered the development and evaluation of emotional health assessment tools. To address this gap, we developed the Contactless Affect Recognition Database (CARD), built from data gathered across 53 participants, which is designed to support the advancement of robust and scalable models for emotion and mental disorder detection, particularly in online and social media–enabled environments such as video conferencing, live streaming, and virtual classrooms. The database includes RGB and infrared facial images, peak facial clips, breath, heart waveforms, and other physiological parameters recorded during machine interactions, enabling cross-platform applications from controlled laboratory settings to real-world social media contexts.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":"13 5","pages":"6773-6785"},"PeriodicalIF":4.6,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11644384","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multimodal Rumor Detection via Hierarchical CNN-Transformer Integration and Co-Adaptive Multimodal Fusion","authors":"Yicheng Li;Jiachen Ma;Wei Zhang;Yong Liu","doi":"10.1109/TCSS.2026.3702240","DOIUrl":"https://doi.org/10.1109/TCSS.2026.3702240","url":null,"abstract":"The widespread proliferation of misinformation on social media has raised significant concerns, emphasizing the urgent need for accurate multimodal rumor detection to ensure information authenticity. However, existing approaches remain limited by inadequate modeling of visual features, insufficient cross-modal semantic alignment, and rigid fusion strategies that fail to adapt to varying modality contributions. To address these challenges, we propose a novel framework: hierarchical co-adaptive multimodal model (HiCoMM). Specifically, to mitigate the limitation of existing visual encoders that fail to capture both local forgeries and global semantics, HiCoMM introduces a hierarchical visual encoder combining convolutional neural networks (CNNs) and Transformer layers to jointly extract fine-grained textures and holistic semantic information. Furthermore, to handle semantic misalignment and modality imbalance during multimodal integration, we design a co-adaptive multimodal fusion module. Within this module, a cross-modal multihead co-attention mechanism establishes precise alignment between visual patches and textual tokens to alleviate semantic mismatches, while a gating-based dynamic fusion mechanism adaptively adjusts the contribution of each modality according to sample-specific characteristics, thus overcoming the rigidity of static fusion strategies that often lead to modality imbalance. Experimental results on two real-world multimodal datasets demonstrate that HiCoMM consistently outperforms state-of-the-art methods.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":"13 5","pages":"6077-6095"},"PeriodicalIF":4.6,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097267","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"LLM4GKID: A Multimodal Large Language Model-Driven Framework for Ghost Kitchen Identification","authors":"Weipeng Deng;Yihong Tang;Chaofan Wang;Tianren Yang","doi":"10.1109/TCSS.2026.3650928","DOIUrl":"https://doi.org/10.1109/TCSS.2026.3650928","url":null,"abstract":"The proliferation of ghost kitchens (i.e., delivery-only restaurants without physical storefronts) poses significant challenges for urban food system monitoring and regulatory oversight. These establishments maintain digital visibility on delivery platforms while eluding visibility in the physical public realm, creating information asymmetries that compromise transparency and consumer protection. This work presents LLM4GKID, a comprehensive approach for detecting ghost kitchens by leveraging the sensing capability of large language models to match point of interest (POI) records across platforms. The methodology integrates multiple information sources through a staged pipeline: geographic filtering to identify spatial candidates, language model-based semantic similarity assessment, visual consistency analysis of establishment imagery, and machine learning classification. Central to our contribution is the alignment failure detection mechanism, which systematically identifies delivery-only establishments lacking corresponding entries in crowdsourced review databases. Evaluation on a manually annotated dataset of restaurant POI pairs from Shenzhen, China, demonstrates substantial performance improvements over existing methods adapted for our task. The progressive filtering strategy significantly reduces computational complexity while maintaining high recall by conservatively selecting candidates. Our framework addresses fundamental challenges in category-specific business model detection, where traditional POI conflation approaches fail due to sparse category features and the spatial autocorrelation implied by Tobler’s law. LLM4GKID overcomes these limitations through the integration of multimodal evidence and negative matching logic, enabling the accurate identification of establishments with asymmetric digital presence patterns. The framework allows downstream research in food access equity, regulatory compliance monitoring, and broader applications to other business models with asymmetric digital footprints.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":"13 5","pages":"6288-6303"},"PeriodicalIF":4.6,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097319","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DISCERN: Disentangled Multilingual Mental Health Risk Detection With Calibrated, High-Recall Predictions","authors":"Anshumala Rakesh;Annavarapu Chandra Sekhara Rao","doi":"10.1109/TCSS.2026.3724689","DOIUrl":"https://doi.org/10.1109/TCSS.2026.3724689","url":null,"abstract":"Identifying mental health risk on social media is high-stakes, demanding low false negative rates (FNRs) and calibrated, trustworthy predictions. Prior work typically fuses linguistic and semantic signals without psycholinguistic grounding or disentanglement, lacks integrated calibration, prioritizes standard metrics over FNR, and remains largely English-only. We propose a disentangled multilingual mental health risk detection with calibrated, high-recall predictions (DISCERN), a safety-oriented framework that disentangles psycholinguistically grounded linguistic signals from semantic content via dual encoders, dynamically fused through hierarchical gated attention (HGA). Evaluated on seven social media datasets spanning suicidal ideation, stress, and depression in English, Hindi, and Hinglish, DISCERN incorporates uncertainty quantification and calibration during training, reports expected calibration error (ECE), and applies posthoc calibration. It achieves lower FNR than all supervised baselines across all datasets, including a <inline-formula><tex-math>${boldsymbol{sim}}$</tex-math></inline-formula>9% relative reduction over the strongest baseline on the Hinglish suicide-risk set, while producing statistically well-calibrated predictions, thereby supporting ethical, human–artificial intelligence (AI) cooperative triage for multilingual mental health monitoring.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":"13 5","pages":"6704-6715"},"PeriodicalIF":4.6,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097421","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Detecting Speaking Intention From Motion and Physiological Data to Support Leadership in VR Group Discussions","authors":"Chenghao Gu;Jiadong Chen;Tianyuan Yang;Boxuan Ma;Shin’ichi Konomi","doi":"10.1109/TCSS.2026.3716220","DOIUrl":"https://doi.org/10.1109/TCSS.2026.3716220","url":null,"abstract":"Effective leadership in virtual reality (VR) group discussions is challenged by the scarcity of nonverbal cues, making it difficult to infer members’ communicative readiness and manage turn-taking. This study introduces a multisensing approach to detect latent speaking intentions—both achieved and unachieved-by integrating motion data from commercial VR headsets with physiological signals. We propose a late-fusion deep learning model, omni-scale multivariate long short-term memory (OS-MLSTM) with cross attention, designed to capture temporal dependencies across modalities. Extensive validation shows that fusing motion and physiological features outperforms single-modality sensing in the mixed-subject setting with area under the receiver operating characteristic curve (AUROC) of 0.9057. Stricter validation settings, including leave-one-participant-out (AUROC: 0.7547) and purged cross validation (AUROC: 0.7752), indicate that unseen-user generalization still remains challenging. These findings provide a sensing foundation for leader-support mechanisms, such as real-time intention cues and summary dashboards, that may support leaders to identify latent opportunities for participation, thereby addressing problematic dynamics, such as intention bursts and participation imbalance, in VR group discussions.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":"13 5","pages":"6035-6047"},"PeriodicalIF":4.6,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097441","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}