IEEE Transactions on Computational Social Systems最新文献_第6页

Large Language Model Embedding for Cold-Start Item Recommendation via Data Augmentation and Regularization 基于数据增强和正则化的冷启动项目推荐大语言模型嵌入

IF 4.6 2区计算机科学

IEEE Transactions on Computational Social Systems Pub Date : 2026-10-01 Epub Date: 2026-02-18 DOI: 10.1109/TCSS.2026.3654086

Kangyi Xie;Ayong Ye;Chuang Huang;Jing Chen;Fu Liao

{"title":"Large Language Model Embedding for Cold-Start Item Recommendation via Data Augmentation and Regularization","authors":"Kangyi Xie;Ayong Ye;Chuang Huang;Jing Chen;Fu Liao","doi":"10.1109/TCSS.2026.3654086","DOIUrl":"https://doi.org/10.1109/TCSS.2026.3654086","url":null,"abstract":"The cold-start problem constitutes a persistent challenge in recommender systems (RecSys). Recent advances in large language model (LLM) for natural language processing have inspired researchers to utilize their semantic understanding and knowledge extraction capabilities in recommendation tasks. LLM shows clear advantages in addressing cold-start items. However, current methods often rely on direct online LLM inference. This approach causes high computational costs and latency. To overcome these limitations, we propose large language model embedding for cold-start item recommendation via data augmentation and regularization (LLM-DAR). Our method transfers LLM capabilities to RecSys through semantic embeddings. This reduces computational costs and latency in online recommendations, making the system more suitable for high-concurrency real-time recommendation scenarios. Specifically, we first use LLM to extract semantic embeddings from item descriptions. Based on these embeddings, we implement data augmentation by associating cold-start items with similar popular items from users’ historical interactions, generating synthetic interaction samples to bridge knowledge gaps. To ensure effective learning of semantic relationships, we design a regularization constraint. This constraint pulls semantically similar items closer in the vector space.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":"13 5","pages":"6316-6325"},"PeriodicalIF":4.6,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097374","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}

引用次数: 0

GTC-Inf: Dual Graph Transformers With Contrastive Learning for Information Diffusion Prediction 基于对比学习的信息扩散预测对偶图变换

IF 4.6 2区计算机科学

IEEE Transactions on Computational Social Systems Pub Date : 2026-10-01 Epub Date: 2026-07-21 DOI: 10.1109/TCSS.2026.3712331

Panyang Yu;Pengfei Jiao;Qing Bao;Hongqian Chen;Zhongliang Zhang

{"title":"GTC-Inf: Dual Graph Transformers With Contrastive Learning for Information Diffusion Prediction","authors":"Panyang Yu;Pengfei Jiao;Qing Bao;Hongqian Chen;Zhongliang Zhang","doi":"10.1109/TCSS.2026.3712331","DOIUrl":"https://doi.org/10.1109/TCSS.2026.3712331","url":null,"abstract":"With the rapid development of social media, the task of information diffusion prediction is playing an increasingly important role in understanding the path of information dissemination in social networks. Previous works have gradually recognized the critical impact of both information propagation structure and social network structure in capturing dependencies among users with pairwise interactions, yet they have overlooked the long-distance dependencies among users embedded in those graphs. For instance, two users with similar interests may repost the same post written by a distant user who is not friends with any of them. Also, the correlation between the two graphs has not been studied before. To address this issue, we propose a dual <bold>graph <bold>transformer with <bold>contrastive learning for <bold>information diffusion prediction (GTC-Inf) framework. Specifically, we construct a social graph and a diffusion graph based on users’ social relationships and diffusion relationships from information cascades, respectively. Subsequently, we incorporate graph transformers to jointly learn the <inline-formula> <tex-math>$k$</tex-math> </inline-formula>-hop dependencies among users on both graphs. In addition, to capture the correlated information learned from those two modules, we utilize contrastive learning to compare the different representations obtained from the two graphs for each cascade, thereby assisting model training. Finally, we leverage an attention mechanism to fuse the information for prediction. Experimental results on four public datasets show that GTC-Inf achieves competitive performance against strong diffusion prediction baselines.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":"13 5","pages":"5996-6006"},"PeriodicalIF":4.6,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097621","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}

引用次数: 0

Attributed Network Anomaly Detection via Feature Masking and Anomaly Enhancement 基于特征掩蔽和异常增强的属性网络异常检测

IF 4.6 2区计算机科学

IEEE Transactions on Computational Social Systems Pub Date : 2026-10-01 Epub Date: 2026-07-31 DOI: 10.1109/TCSS.2026.3713796

Wenkai Zhang;Chaobo He;Junwei Cheng;Peng Mei;Feiyu Peng;Youda Mo

{"title":"Attributed Network Anomaly Detection via Feature Masking and Anomaly Enhancement","authors":"Wenkai Zhang;Chaobo He;Junwei Cheng;Peng Mei;Feiyu Peng;Youda Mo","doi":"10.1109/TCSS.2026.3713796","DOIUrl":"https://doi.org/10.1109/TCSS.2026.3713796","url":null,"abstract":"Anomaly detection in attributed networks has extremely important application value, and graph neural networks (GNNs) based methods for it have been extensively proposed. However, the presence of anomalous nodes breaks the homophily assumption of GNNs, causing two unresolved problems: anomaly contamination and low anomaly discriminability, which often lead to suboptimal anomaly detection performance. In view of this, we propose a reconstruction-based attributed network anomaly detection method via feature masking and anomaly enhancement (FMAE). Specifically, to adaptively enhance anomaly discriminability, FMAE introduces dual-channel spectral filtering and an attention-based feature fusion mechanism. For anomaly contamination, FMAE designs a fine-grained masking module, which can automatically suppress the feature propagation of anomalous nodes. To further enhance the detection capability, FMAE utilizes a structure-aware module to measure the structural consistency of each node. Meanwhile, FMAE devises a reconstruction loss, which can alleviate the problem that abnormal nodes easily dominate the model optimization process. Compared with state-of-the-art baselines, extensive experiments conducted on benchmark datasets demonstrate the superiority of FMAE.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":"13 5","pages":"5956-5967"},"PeriodicalIF":4.6,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097589","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}

引用次数: 0

Multilingual Emotion Detection in Social Media Using an Attention-Enhanced and Explainable Machine Learning Framework 使用注意力增强和可解释的机器学习框架的社交媒体多语言情感检测

IF 4.6 2区计算机科学

IEEE Transactions on Computational Social Systems Pub Date : 2026-10-01 Epub Date: 2026-07-20 DOI: 10.1109/TCSS.2026.3710752

Muhammad Ahmad;Abubakar Siddique;Rita Orji;Segun Olatinwo;Grigori Sidorov

{"title":"Multilingual Emotion Detection in Social Media Using an Attention-Enhanced and Explainable Machine Learning Framework","authors":"Muhammad Ahmad;Abubakar Siddique;Rita Orji;Segun Olatinwo;Grigori Sidorov","doi":"10.1109/TCSS.2026.3710752","DOIUrl":"https://doi.org/10.1109/TCSS.2026.3710752","url":null,"abstract":"Emotions play a central role in human experience, influencing decisions, behaviors, and social interactions. Despite substantial advances in natural language processing, detecting emotions in multilingual and code-mixed texts remains challenging due to the linguistic diversity of social media users, particularly in low-resource languages. While prior work has focused mainly on monolingual approaches, with limited exploration of multilingual scenarios. This study addresses multilingual emotion detection by creating a machine learning framework enhanced with a custom attention mechanism and fine-tuning strategy. The proposed custom attention mechanism is devised to capture emotionally salient information and improve classification accuracy. Two complementary approaches are explored: 1) a joint multilingual model based on a universal emotion classifier for multiple languages; and 2) a translation-based model that standardizes all inputs into a single target language. Additionally, explainable artificial intelligence (XAI) techniques are implemented to interpret the model’s decisions and enhance transparency. To obtain a proof-of-concept, two existing datasets are transformed into three new multilingual resources with four additional emotion categories. Experiments are conducted using both conventional and advanced machine learning models—integrated with the custom attention mechanism—to evaluate the system’s effectiveness for multilingual emotion recognition tasks. The proposed model achieved superior performance, with accuracy-scores of <inline-formula><tex-math>$93.1%,79.6%$</tex-math></inline-formula>, and <inline-formula><tex-math>$93.3%$</tex-math></inline-formula> for augmented English, augmented Urdu, and multilingual datasets, respectively.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":"13 5","pages":"5817-5830"},"PeriodicalIF":4.6,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097710","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}

引用次数: 0

Voting or Evaluation: An E-CARGO Perspective 投票或评估：电子货物的视角

IF 4.6 2区计算机科学

IEEE Transactions on Computational Social Systems Pub Date : 2026-10-01 Epub Date: 2026-08-12 DOI: 10.1109/TCSS.2026.3720344

Haibin Zhu;Saeid Nahavandi;Sam Tak Wu Kwong;Imre J. Rudas

{"title":"Voting or Evaluation: An E-CARGO Perspective","authors":"Haibin Zhu;Saeid Nahavandi;Sam Tak Wu Kwong;Imre J. Rudas","doi":"10.1109/TCSS.2026.3720344","DOIUrl":"https://doi.org/10.1109/TCSS.2026.3720344","url":null,"abstract":"Voting is a widely accepted method for decision-making and for assigning positions to members of committees. For instance, each year, most IEEE Societies or Councils conduct elections to renew its Executive Committee (ExCom) or Administrative Committee (AdCom) in accordance with the Society’s or council’s bylaws. However, traditional voting methods, though easy to follow and broadly accepted, may not always yield the most effective outcomes. This article proposes a new, computation-based approach to committee member selection, grounded in the environments-classes, agents, roles, groups, and objects (E-CARGO) model and the role-based collaboration (RBC) methodology. Developed and refined over the past two decades, E-CARGO/RBC provides a solid foundation for modeling and solving complex collaborative and decision-making problems, particularly those involving team-based dynamics. Through comparative analysis and a case study, this work demonstrates how the proposed computational approaches surpass the traditional way in the selection of ExCom/AdCom members, and achieve more effective position assignments than traditional voting-based approaches.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":"13 5","pages":"5514-5524"},"PeriodicalIF":4.6,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097873","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}

引用次数: 0

VATOM: A Value-Aware Transaction Ordering Mechanism for Efficient Blockchain Scheduling VATOM：一种高效区块链调度的价值感知事务排序机制

IF 4.6 2区计算机科学

IEEE Transactions on Computational Social Systems Pub Date : 2026-10-01 Epub Date: 2026-07-27 DOI: 10.1109/TCSS.2026.3709857

Xinlei Sheng;Chen Wang;Jian Shen;Han-Chieh Chao

引用次数: 0

SDADL: SVD-Based Dual Adaptive Debiasing Learning for Personalized Recommendation SDADL：基于奇异值分解的个性化推荐双自适应去偏学习

IF 4.6 2区计算机科学

IEEE Transactions on Computational Social Systems Pub Date : 2026-10-01 Epub Date: 2026-08-07 DOI: 10.1109/TCSS.2026.3708165

Zhenzhen Hu;Yang Wang;Wenhao Qian;Zijie Song;Qian Zuo;Jing Ren;Richang Hong

{"title":"SDADL: SVD-Based Dual Adaptive Debiasing Learning for Personalized Recommendation","authors":"Zhenzhen Hu;Yang Wang;Wenhao Qian;Zijie Song;Qian Zuo;Jing Ren;Richang Hong","doi":"10.1109/TCSS.2026.3708165","DOIUrl":"https://doi.org/10.1109/TCSS.2026.3708165","url":null,"abstract":"Personalized recommendation systems often suffer from various biases in data-driven paradigms, which can significantly degrade their fairness and generalization. Existing debiasing approaches typically rely on strong assumptions about bias types or purely statistical corrections, limiting their adaptability to unknown and changeable bias patterns, which fail to capture the complexities of human behavior and decision-making. To address this challenge, we propose a novel SVD-based dual adaptive debiasing learning (SDADL) framework. In SDADL, we distinguish between target samples (TS), which are observed positive interactions in training, and flaw samples (FS), which are highly ranked but potentially spurious positives. During training, node embeddings are decomposed via singular value decomposition (SVD) and further refined through dual adaptive learning pathways dedicated to TS and FS, respectively. Notably, the model is not explicitly constrained by the loss on the original embeddings; instead, it adaptively balances dual path learning signals under weak supervision, thereby discovering and mitigating hidden biases in a self-guided manner. Experiments demonstrate that SDADL consistently enhances base GCN models in a plug-and-play form and is effective in both supervised and self-supervised learning scenarios.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":"13 5","pages":"5706-5718"},"PeriodicalIF":4.6,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097027","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}

引用次数: 0

SemAlignRec: A Large Language Model-Driven Cross-Modal Collaborative–Semantic Recommendation Framework SemAlignRec：一个大型语言模型驱动的跨模态协同语义推荐框架

IF 4.6 2区计算机科学

IEEE Transactions on Computational Social Systems Pub Date : 2026-10-01 Epub Date: 2026-01-23 DOI: 10.1109/TCSS.2025.3640149

Zongyang Wang;Jun Fan;Qian Gao;Zhixue Zhang;Guohui Ding

{"title":"SemAlignRec: A Large Language Model-Driven Cross-Modal Collaborative–Semantic Recommendation Framework","authors":"Zongyang Wang;Jun Fan;Qian Gao;Zhixue Zhang;Guohui Ding","doi":"10.1109/TCSS.2025.3640149","DOIUrl":"https://doi.org/10.1109/TCSS.2025.3640149","url":null,"abstract":"Recommender systems are increasingly vital in e-commerce and social media, yet traditional collaborative filtering and deep learning methods still face challenges in fine-grained interest modeling and data sparsity. Large language models (LLMs), with strong semantic understanding and reasoning capabilities, excel in cold-start and long-tail scenarios. However, the modality gap between low-dimensional collaborative signals and LLMs’ contextual embeddings leads to fusion difficulties and semantic distortion. To address this, we propose SemAlignRec, a unified recommendation framework that enhances fusion through a model-agnostic collaborative–semantic alignment mechanism. Specifically: 1) <italic>deep semantic encoding and graph structural enhancement: leveraging LLMs to encode user and item textual attributes into high-quality semantic embeddings, which are further refined by a multilayer deep semantic encoder; a graph enhancement module incorporating residual connections, node attention, and graph perturbations strengthens collaborative embeddings and facilitates their fusion with semantic embeddings; and 2) <italic>transmodal fusion and self-supervised optimization: integrating multihead attention, gated fusion, and contrastive self-supervision to achieve precise fusion of collaborative and semantic embeddings. Experiments on multiple datasets show that SemAlignRec delivers substantial performance gains, achieving an overall average improvement of about 6.6% over the compared baselines. In particular, compared with the latest baseline DALR, SemAlignRec obtains an average gain of approximately 9.8% on key metrics for the Amazon and Yelp datasets, demonstrating its strong practical potential.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":"13 5","pages":"6597-6608"},"PeriodicalIF":4.6,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097293","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}

引用次数: 0

Coevolutionary Dynamics of Information and Influence in Social Networks 社会网络中信息和影响的共同进化动力学

IF 4.6 2区计算机科学

IEEE Transactions on Computational Social Systems Pub Date : 2026-10-01 Epub Date: 2026-07-28 DOI: 10.1109/TCSS.2026.3713649

Fuzhong Nian;Guocui Liu;Zhen Zhang

{"title":"Coevolutionary Dynamics of Information and Influence in Social Networks","authors":"Fuzhong Nian;Guocui Liu;Zhen Zhang","doi":"10.1109/TCSS.2026.3713649","DOIUrl":"https://doi.org/10.1109/TCSS.2026.3713649","url":null,"abstract":"The dynamic coupling between information propagation and individual influence diffusion in social networks is addressed by an influence–information coevolutionary propagation model. Grounded in non-Bayesian social learning theory, the model characterizes the mechanism through which individuals enhance their own influence by observing and imitating high-influence neighbors, and an susceptible–infected (SI)–susceptible (SIS) hybrid dynamical framework is employed to separately describe the irreversible information propagation process and the reversible influence learning process. By introducing an influence disparity-driven transmission rate function, the accelerating effect of high-influence individuals on information dissemination is quantified, together with the feedback enhancement effect of information propagation on individual influence. Numerical simulations and bounded public-data validation based on Sina Weibo propagation traces show that the initial seed’s influence significantly affects propagation speed, the dynamic influence update mechanism can reshape the influence distribution landscape in the network, and under the stated mean-field approximation, the coupling is associated with a lower effective early-growth bound. The robustness of these findings is further assessed through one-way parameter sensitivity analysis, comparison against five representative proxy/variant baseline models, confidence-interval estimation of the fitting accuracy, and cross-topology checks on public network datasets. This study provides a theoretical framework for understanding the coevolution of content dissemination and influence accumulation in social networks and has practical value in social media marketing strategy formulation and opinion leader identification.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":"13 5","pages":"5968-5981"},"PeriodicalIF":4.6,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097619","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}

引用次数: 0

Coevolution of Supervision and Cooperation Under Environmental Feedback in Public Good Games 公共物品博弈中环境反馈下监督与合作的协同演化

IF 4.6 2区计算机科学

IEEE Transactions on Computational Social Systems Pub Date : 2026-10-01 Epub Date: 2025-11-11 DOI: 10.1109/TCSS.2025.3624889

Haili Liang;Tao Sun;Zhao Zhou;Ming Cao

{"title":"Coevolution of Supervision and Cooperation Under Environmental Feedback in Public Good Games","authors":"Haili Liang;Tao Sun;Zhao Zhou;Ming Cao","doi":"10.1109/TCSS.2025.3624889","DOIUrl":"https://doi.org/10.1109/TCSS.2025.3624889","url":null,"abstract":"Understanding the emergence and stability of cooperation in resource-sharing systems is fundamental to evolutionary game theory and sustainability science. Existing studies of public goods games have largely overlooked the bidirectional coupling between strategic behavior and environmental dynamics. To bridge this gap, we propose a coevolutionary framework for threshold-based public goods games that integrates environmental feedback and supervisory punishment mechanisms. In our model, the strategies of the agents evolve in conjunction with the ecological states, while supervisory incentives regulate individual behavior. Using replicator dynamics and bifurcation analysis, we identify critical conditions for the stability of internal equilibria and demonstrate how cooperation thresholds and supervisory incentives act as bifurcation parameters. Our results reveal the occurrence of Hopf and heteroclinic bifurcations, highlighting complex dynamical patterns such as oscillatory cooperation. Simulations confirm the theoretical predictions, showing that cooperation and regulatory incentives coevolve adaptively under changing ecological constraints. This work advances the understanding of feedback-driven cooperation and provides novel insights into designing adaptive governance mechanisms in complex socioecological systems.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":"13 5","pages":"6547-6556"},"PeriodicalIF":4.6,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097840","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}

引用次数: 0