Scope

IEEE Transactions on Computational Social Systems focuses on such topics as modeling, simulation, analysis and understanding of social systems from the quantitative and/or computational perspective. “Systems” include man-man, man-machine and machine-machine organizations and adversarial situations as well as social media structures and their dynamics. More specifically, the proposed transactions publishes articles on modeling the dynamics of social systems, methodologies for incorporating and representing socio-cultural and behavioral aspects in computational modeling, analysis of social system behavior and structure, and paradigms for social systems modeling and simulation. The journal also features articles on social network dynamics, social intelligence and cognition, social systems design and architectures, socio-cultural modeling and representation, and computational behavior modeling, and their applications.

Special Issue on Perception-Aware Anomaly Understanding in Computational Social Systems: Modeling and Assessment
Submission Date: 2026-06-30

Introduction

Contemporary computational social systems encompass complex human-human, human-machine, and machine-machine organizations within immersive metaverse environments and multimedia-rich social platforms that demand sophisticated quality assessment and anomaly understanding mechanisms. Perception-Aware Anomaly Understanding (PAAU) integrates perceptual quality assessment with intelligent anomaly detection to evaluate both functional performance and perceptual impact across multimodal social interactions. Unlike traditional anomaly detection, which focuses on statistical deviations in isolated contexts, PAAU provides a holistic framework to assess anomalous behaviors while considering their effects on user experience, multimedia content quality, and system trustworthiness in diverse social computing environments.

The rapid integration of large-scale AI models, multimodal systems, and edge-cloud architectures into social platforms introduces complex interaction patterns that conventional methods struggle to address. These systems operate across heterogeneous environments—spanning mobile apps, AR/VR devices, and IoT-enabled spaces—requiring robust frameworks to ensure reliable performance, content authenticity, and user safety. PAAU tackles these challenges by combining advanced modeling, representation learning, and evaluation methodologies to detect anomalies and assess quality in real-time, while addressing societal concerns such as fairness, privacy, and sustainability. This special issue invites high-quality, original contributions from researchers and practitioners to advance theoretical and practical approaches to PAAU, fostering trustworthy and intelligent computational social systems.

Topics include but are not limited to:

    Perception-aware quality assessment frameworks for social interactions and multimedia content
    Intelligent anomaly detection in social networks, including deepfake and threat identification
    Large AI model applications for multimodal social system analysis and behavior prediction
    Edge-cloud collaborative architectures for scalable quality assessment and real-time anomaly detection
    Multimodal learning frameworks integrating text, image, video, audio, and behavioral data
    Human-AI collaborative systems with trust mechanisms and interaction quality assessment
    Trustworthy AI mechanisms for fairness, bias mitigation, and content authenticity
    Social intelligence and cognition modeling for immersive and hybrid social environments
    Socio-cultural modeling with cross-cultural anomaly detection and adaptive system design
    Green and sustainable computing strategies for energy-efficient social system analysis

By addressing these challenges, this special issue aims to establish foundational knowledge for next-generation computational social systems that are intelligent, reliable, and socially responsible.

Important Dates:

    Paper Submission Deadline: June 30, 2026
    First Decision Deadline: September 30, 2026
    Revision Deadline Deadline: November 1, 2026
    Final Decision Deadline: November 30, 2026

Guest Editors:

    Jing Liu, University of British Columbia, Canada
    Yang Liu, Tongji University, China
    Boan Chen, Shanghai Jiao Tong University, China
    Chris Wei Zhou, Cardiff University, UK
    Jelena Mišić, Toronto Metropolitan University, Canada
    Victor C. M. Leung, SMBU, China / UBC, Canada
    Abdulmotaleb El Saddik, University of Ottawa, Canada

Special Issue on Large-scale and Generative AI for Economic and Business Forecasting: Modeling, Technologies, and Applications
Submission Date: 2026-06-30

Introduction

The rapid evolution of large-scale artificial intelligence (AI) and the disruptive emergence of generative AI (GenAI) are fundamentally reshaping the landscape of economic and business forecasting. These technologies offer unparalleled capabilities to process vast and heterogeneous datasets, model complex nonlinear relationships, and generate synthetic data and plausible future scenarios. This paradigm shift holds the potential to enhance the accuracy, timeliness, and interpretability of predictions across diverse domains, ranging from macroeconomic nowcasting to highly granular demand forecasting.

This special issue aims to provide a premier platform for disseminating cutting-edge research on the integration of large-scale AI (e.g., deep learning, foundation models) and GenAI (e.g., Large Language Models (LLMs), Generative Adversarial Networks (GANs), and diffusion models) into predictive analytics for economics and business. We invite submissions addressing theoretical developments, methodological innovations, and practical applications that tackle longstanding challenges and uncover new opportunities for advancing forecasting practice.

Topics of Interest

We invite original research and review articles that contribute to the advancement of this field. Topics of interest include, but are not limited to:

    Advanced Modeling Techniques: Novel architectures and algorithms leveraging foundational models, transformers, LLMs, GANs, and other generative techniques for time-series forecasting and nowcasting.
    Multi-Agent Simulation Systems: Agent-based modeling (ABM) simulating market dynamics, consumer behavior, supply chain interactions, and their use for predictive purposes.
    Integration of Multimodal Data: Leveraging LLMs to analyze and integrate multimodal data (e.g., text, image, sound, video) with traditional structured data for enhanced prediction accuracy.
    Causal Inference and Explainability: Techniques for causal discovery, reasoning, and generating interpretable forecasts within LLM and agent-based frameworks.
    Causal Inference and Explainable AI (XAI): Developing methods for causal discovery, reasoning, and generating interpretable forecasts within large-scale and generative AI frameworks.
    Decision Optimization: Building end-to-end systems where AI models not only predict outcomes but also generate actionable insights, recommendations, and automated decisions for optimal business decisions (e.g., in pricing, inventory management, and investment).
    Addressing Forecasting Challenges: Applications tackling key issues like demand forecasting, financial market prediction, macroeconomic indicator forecasting, and risk assessment.
    Robustness and Ethics: Studies on the robustness, bias, fairness, and ethical implications of using large-scale AI models in sensitive economic forecasting.
    Human-AI Collaboration: Frameworks for effective collaboration between human experts and AI agents in the forecasting pipeline.

Important Dates

    Submission Deadline: June 30, 2026
    First Round of Reviews: October 30, 2026
    Revised Manuscripts Due: December 31, 2026
    Final Decision: January 31, 2027
    Publication Date: Q2 2027

Submission Guidelines
Authors should prepare their manuscripts according to the submission guidelines of the IEEE Transactions on Computational Social Systems. Manuscripts should be submitted through the online submission system at: https://ieee.atyponrex.com/journal/tcss, and select “Special Issue” of “Large-scale and Generative AI for Economic and Business Forecasting: Modeling, Technologies, and Applications” under the Manuscript Category. All submissions will undergo a rigorous, single-blind peer-review process.

Guest Editors

    Xuerong Li, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, lixuerong@amss.ac.cn
    Tao Hong, University of North Carolina at Charlotte, hong@charlotte.edu
    Shouyang Wang, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, sywang@amss.ac.cn
    Jue Wang, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, wjue@amss.ac.cn
    Xiuting Li, University of Chinese Academy of Sciences, lixiuting@ucas.ac.cn
    Xiaoqian Wang, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, xiaoqian.wang@amss.ac.cn

Special Issue on Cyber-Physical-Social Intelligence: State-of-the-art, Perspectives, and Challenges
Submission Date: 2026-11-10

Introduction

Cyber-Physical-Social Systems (CPSS) combine cyber, physical, and social spaces, enabling systems that simultaneously perceive, interpret, and interact with the physical environment and human behaviors. Through this deep cross-domain integration, CPSS are increasingly capable of context-aware monitoring, adaptive control, personalized assistance, and collaborative decision support. The shift from perception to cognition and from basic interconnection to intelligent coordination motivates the development of Cyber-Physical-Social Intelligence (CPSI), which aims to provide users with the ability to comprehend complex scenarios, anticipate future dynamics, and make autonomous decisions.

Recent advances in CPSI have rapidly transitioned from conventional rule-based or domain-specific methods to more integrated forms of cognition and autonomy. Despite rapid progress in multimodal fusion, holistic awareness, and distributed intelligence, CPSI still faces several fundamental challenges in model construction, intelligent knowledge discovery, decision-making, high-performance computing, and system security. These challenges include accurately capturing coupled cyber-physical-social dynamics, ensuring robust multimodal representation and cross-domain alignment, modeling cognitive behaviors under uncertainty, and maintaining real-time digital-twin synchronization. Knowledge discovery remains difficult due to heterogeneous and incomplete data, ambiguous human intentions, and the need for reliable semantic reasoning, causal inference, and emergent behavior detection. Intelligent decision-making is hindered by the difficulty of learning generalizable policies, coordinating multi-agent planning, predicting long-term behavioral tendencies, and translating high-level reasoning into dependable actions. Scalable real-time CPSI is constrained by the computational demands of perception and foundation models, high-frequency synchronization, and distributed learning under strict resource limitations. Moreover, achieving secure and trustworthy CPSI is complicated by expanded cross-domain attack surfaces, privacy risks, vulnerabilities in generative models, and the need for transparent, resilient intelligence across cyber-physical-social ecosystems.

This Special Issue invites high-quality original contributions from researchers and practitioners to advance theoretical and practical approaches in CPSI, enhancing cognitive reasoning, behavioral prediction, cross-domain perception, autonomous adaptation, human-AI collaboration, and system resilience, to push the boundaries toward truly intelligent, trustworthy, and self-evolving CPSS.

Topics include but are not limited to:

    AI/ML-driven sensing and perception for cyber, physical, and social environments
    Cognitive behavior modeling and human-machine interaction in CPSI
    Digital twin modeling and real-time synchronization in CPSS
    Deep multimodal fusion architectures for heterogeneous CPSS data
    Embodied intelligence and CPSI-driven agents for adaptive interaction and decision-making
    LLM-based semantic reasoning, cross-domain alignment, and causal inference
    Reinforcement learning and optimal control for adaptive CPSS behavior
    Generative AI-based modeling, simulation, and prediction of CPSS dynamics
    Agent-based simulation of social interaction and collective intelligence
    Cognitive situation awareness and intent prediction in dynamic CPSI environments
    LLM-driven multi-agent systems for planning and collective decision-making
    CPSI for metaverse governance, safety, and trustworthy digital ecosystems
    Intelligent defense and resilience against cyber-physical-social attacks
    Federated learning and privacy-preserving techniques for large-scale CPSS
    Explainable, transparent, and trustworthy AI models for CPSI decision-making
    Data-driven intelligent services in CPSS

Important Dates:

    Paper Submission Deadline: November 10, 2026
    First Decision Deadline: January 15, 2027
    Revision Deadline: February 15, 2027
    Final Decision Deadline: March 15, 2027

Submission Guidelines:
Authors should prepare their manuscripts according to the submission guidelines of the IEEE Transactions on Computational Social Systems. Manuscripts should be submitted through the online submission system at: https://ieee.atyponrex.com/journal/tcss, and select “Special Issue” of “Cyber-Physical-Social Intelligence: State-of-Art, Perspectives, and Challenges” under the Manuscript
Category. All submissions will undergo a rigorous, single-blind peer-review process.

Guest Editors:

    Xiaokang Wang, Zhengzhou University, China
    Parimala Thulasiraman, University of Manitoba, Canada
    Sin G. Teo, A*STAR, Singapore
    Xueqin Liang, Xidian University, China