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 Few-shot/Zero-shot Learning for Knowledge Discovery in Social Networks
提出日: 2024-12-28

In the era of digital connectivity and social media, social networks have become massive repositories of information and interactions among individuals. These interactions encompass a wide array of topics, from personal interests and social relationships to discussions about events, products, and more. Extracting meaningful insights and knowledge from such vast and heterogeneous data is a challenge that traditional methods struggle to address. The necessity for “Few-shot/Zero-shot Learning for Knowledge Discovery in Social Networks” arises from the limitations of conventional techniques in dealing with the unique characteristics of social network data. The traditional approaches often require labeled training data and predefined categories, which may not be feasible in the context of evolving, dynamic, and unstructured social network data. This is where Few-shot/Zero-shot learning becomes highly relevant.

Guest Editors:

    Junyang Chen, Shenzhen University, China
    Jingcai Guo, The Hong Kong Polytechnic University, Hong Kong SAR, China
    Huan Wang, Huazhong Agricultural University, China
    Zhenghua Xu, Hebei University of Technology, China
    Mengzhu, Wang, Hefei University of Technology, China
    Nan Yin, Mohamed bin Zayed University of Artificial Intelligence, United Arab Emirates
    Victor C.M. Leung, Shenzhen University / The University of British Columbia, China / Canada

Submissions for this issue will close on December 28, 2024

Special Issue on Collaborative Learning and Distributed Intelligence in Cyber-Physical-Social Systems and Applications
提出日: 2024-12-31

Along with the rapid development of AI and machine learning techniques, Cyber-Physical-Social System (CPSS) now increasingly enables the intelligent human-computer interactions among human organizations, cyber networks, and physical systems through smart sensor networks associated with cloud/edge computing infrastructures. Currently, with the fundamental support of novel technologies including Artificial Intelligence of Things (AIoT) and big data analytics with large models, complex CPSS, applied in Industry 4.0, smart healthcare systems, and intelligent transportation systems, etc., leads to a promising and transdisciplinary intersection of AI, information science, and cognitive computing, etc.

In particular, distributed intelligence exploits cooperation between devices, communication infrastructures, and edge computing systems, which may optimally support CPSS by handling the distributed data independently in parallel. Collaborative learning integrates distributed learning between different peers, which can enhance CPSS to further make full use of cooperation between entities specializing in different tasks and data modalities. Therefore, the quality of CPSS-enhanced services and applications can be significantly improved from the incorporation of collaborative learning with distributed intelligence, which can efficiently manage and process heavily-loaded resources and big data mining in decentralized paradigms, toward next generation models for design and building of distributed smart applications. However, it is still facing not a few challenges, such as how to realize real-time processing as one of the fundamental requirements in communication, computation, and storage in CPSS when facing massive human-generated data every day; How to deal with the large-scale and distributed data generated by different sensors to ensure low-latency services; How to solve the heterogeneous nature and discover insightful knowledge from the multi-modality data with high-efficiency learning algorithms.

This special issue aims at: i) providing a platform for researchers and practitioners to demonstrate their novel research achievements and applications of collaborative learning and distributed intelligence in CPSS today and the foreseeable future, and ii) exploring potential research opportunities in emerging trends on the integration of physical distributed computing infrastructure, intelligent data-driven cyberspace, and human social intervention in specific application domains.

Topics of interest to this special issue include, but are not limited to:

    Collaborative learning in smart CPSS
    Distributed intelligence in end-edge-cloud systems
    Collaborative computing for smart human-machine interface design
    Multi-agent distributed system with collaborative learning
    Collaborative learning and distributed intelligence for smart manufacturing
    Collaborative learning with intelligent IoT for smart healthcare
    Big data analytics and application with collaborative learning in CPSS
    Theory and application of distributed intelligence in CPSS
    Federated learning and multi-agent reinforcement learning in CPSS
    Collaborative learning with privacy, security, and trust concerns in CPSS

Important Dates:

    Paper Submission Deadline: Dec. 31, 2024
    First Round of Reviews Deadline: Mar. 31, 2025
    Submission of Revision Deadline: May 31, 2025
    2nd Round of Reviews Deadline: Jul. 31, 2025
    Decision of Acceptance Deadline: Aug. 31, 2025

Guest Editors:

    Xiaokang Zhou, Shiga University, Japan
    Kevin Wang, The University of Auckland, New Zealand
    Jianhua Ma, Hosei University, Japan
    Vincenzo Piuri, University of Milan, Italy

Special Issue on Large-Scale Knowledge Discovery in Computational Social Systems
提出日: 2025-01-01

Over the last decade, significant progress has been made in understanding the inherent dynamics of social systems. In the current digital era, where each social interaction leaves a digital trace, computational modeling has proven instrumental in untangling the complexities of human behavior, collective dynamics, and societal evolution. This ever-changing landscape of social systems is continuously unfolding, playing a vital role in deciphering the intricate nature of interactions, especially in the domain of large-scale knowledge discovery. Large-scale knowledge discovery within social systems, facilitated by computational models, offers unprecedented advantages. The sheer volume and diversity of data generated in contemporary social interactions provides an expansive canvas for exploration. Leveraging large-scale datasets allows for more comprehensive insights into behavioral patterns, societal trends, and emergent phenomena, fostering a deeper understanding of the complexities inherent in social dynamics.

Nevertheless, this shift toward large-scale knowledge discovery also reveals research gaps. The challenges lie in efficiently harnessing, processing, and deriving meaningful insights from vast and diverse datasets. The adaptability of existing computational models may lag behind the dynamic nature of large-scale social interactions, necessitating efforts to bridge the divide between potential advantages and current limitations. This special issue aims to facilitate a comprehensive exploration of large-scale knowledge discovery through innovative advancements in computational modeling tailored to the intricate dynamics of contemporary social systems. The goal is to advance the field, offering a nuanced understanding of the opportunities and limitations inherent in large-scale knowledge discovery within the complex tapestry of social systems.

This special issue invites original research papers, reviews, and case studies that delve into, but are not limited to, the following topics, with a specific emphasis on large-scale knowledge discovery:

    Agent-based modeling of social interactions
    Network analysis and graph theory applications
    Machine learning and artificial intelligence methodologies for large-scale knowledge discovery
    Dynamics of opinion formation and diffusion in large-scale social networks
    Computational models elucidating cultural evolution in large-scale societies
    Simulation of collective behavior to unravel emergent phenomena in complex social systems
    Applications of computational models in decision-making with a focus on large-scale knowledge discovery
    Innovations in Large-Scale Knowledge Discovery

Important Dates:

    Manuscript submissions due: January 1, 2025
    First round of reviews completed: April 1, 2025
    Revised manuscripts deadline: June 1, 2025
    Second round of reviews completed: July 15, 2025
    Final manuscripts deadline: August 15, 2025

Guest Editors:

    Man-Fai Leung, Anglia Ruskin University, Cambridge, UK, man-fai.leung@aru.ac.uk
    Shiping Wen, University of Technology Sydney, Australia, Shiping.Wen@uts.edu.au
    Wenqi Fan, The Hong Kong Polytechnic University, Hong Kong, China, wenqi.fan@polyu.edu.hk
    Tingwen Huang, Texas A&M University at Qatar, Qatar, tingwen.huang@qatar.tamu.edu

Special Issue on Revolutionizing Social Intelligence with AI Technologies and Sensing Innovations
提出日: 2025-03-30

The advancement of AI and sensing innovations has unveiled unprecedented opportunities to enhance social intelligence. This evolution has not only reshaped the way we understand and interact with the social world but has also led to innovative approaches to solving complex social challenges. The combination of artificial intelligence, sensing technologies, and social science computing presents unparalleled opportunities to create systems capable of comprehending, forecasting, and impacting social dynamics in more precise and efficient manners. This special issue is dedicated to exploring the various aspects of AI and sensing technologies-empowered social intelligence, from the collection of real-time social and environmental data through wearable device and IoT sensors to the analysis of complex social patterns and behaviors using advanced AI algorithms.

The special issue aims to provide a comprehensive platform to showcase research achievements that contribute to the theory, methods, and applications of AI and sensing technology-enhanced social intelligence. We anticipate investigating the developing trends and possibilities presented by this interdisciplinary field to enhance our comprehension of social systems and promote the overall welfare of global communities.

This special issue invites high-quality, original contributions from researchers, practitioners, and technologists working at the forefront of AI and sensing technologies applied to social intelligence. The journal encourages the submission of articles that present the latest research results and reflect on potential research directions and challenges in revolutionizing social intelligence with AI and sensing innovations. Additionally, extended versions of selected high-quality papers from UIC2024, as well as notable conferences such as Ubicomp, KDD, ICDE, AAAI, MOBICOM, SIGCOMM within the field will be invited to enrich the scope of this special issue.

The special issue has the following topics (but are not limited to):

    AI-driven models for social behavior prediction and analysis
    Sensor-based systems for real-time social interaction monitoring
    Foundation models for social network analysis
    Data fusion methods for social applications
    Real-world applications of AI and sensing technologies in social systems
    Innovative contact or non-contact and IoT technologies for social sensing
    Computational models for social dynamics
    Crowd sensing and computing for social cognition
    Ubiquitous sensing and computing for transportation monitoring and problem-solving
    Personalized systems for social care support for vulnerable groups
    Nature-inspired social intelligent systems

Important Dates (Tentative)

    Paper Submission Deadline: March 30, 2025
    First Round of Reviews Deadline: June 15, 2025
    Submission of Revision Deadline: August 30, 2025
    2nd Round of Reviews Deadline: October 30, 2025
    Decision of Acceptance Deadline: November 30, 2025

Guest Editors:

    Runhe Huang, Hosei University, Japan.
    Bin Guo, Northwestern Polytechnical University, China.
    Binbin Zhou, Hangzhou City University, China.
    Xin Yao,Lingnan University, HK SAR, China.
    Vincenzo Piuri, University of Milan, Italy.

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 “Revolutionizing Social Intelligence with AI and Sensing Innovations” under the Manuscript Category. A separate cover letter should be submitted along with your submission, and notably, if the submission is an extension of a previously published high-quality conference paper, a detailed explanation of the significant differences should be provided. For any inquiries, please contact: bbzhou@hzcu.edu.cm