Foundation Models for Multimodal Understanding, Reasoning, and Prediction in Behavioral and Social Computing

Behavioral and social computing is increasingly driven by the need to learn from rich, heterogeneous, and socially grounded data. Recent progress in foundation models provides a powerful basis for multimodal understanding across text, image, video, audio, time series, graphs, sensor streams, and human interaction data. These models are opening new possibilities for capturing behavioral patterns, social dynamics, contextual signals, and cross-modal semantics in complex real-world environments.

This special session aims to bring together researchers working on foundation models and multimodal intelligence for core BESC problems. We welcome contributions that advance multimodal understanding, reasoning, and prediction in domains such as user behavior modeling, social interaction analysis, recommendation and personalization, educational intelligence, health analytics, misinformation analysis, public decision support, and trustworthy human-centered AI. Both methodological innovations and application-oriented studies are encouraged, especially those that address how foundation models can be adapted, aligned, interpreted, and evaluated for behavioral and social computing tasks.

The special session invites submissions addressing, but not limited to, the following areas:

• Multimodal foundation models for behavioral, social, and user-generated data
• Cross-modal representation learning across text, image, video, audio, time series, graphs, logs, and interaction data
• Multimodal understanding of behavior, intention, affect, cognition, and social interaction
• Reasoning over socially grounded multimodal data and human-centered contexts
• Prediction and forecasting of behavioral and social dynamics
• Foundation models for recommendation, personalization, adaptive systems, and user support
• Self-supervised, weakly supervised, and transfer learning for multimodal behavioral signals
• Retrieval, knowledge grounding, and memory-augmented modeling for behavioral and social computing
• Detection tasks, including anomaly detection, misinformation detection, and risk detection
• Temporal, relational, and graph-aware modeling for social networks and behavioral processes
• AI applications in education, healthcare, mental health, smart communities, public services, and consumer behavior
• Trustworthy foundation models, including explainability, fairness, privacy, safety, robustness, and human-centered evaluation

Important Dates

submission instruction

Please use the below links to download the Springer template and to submit your work.

The format of Research Papers should be suitable for original research, which is completed work at the time of submission and, regardless of the length of the paper, is a self-sufficient scientific contribution. Selected papers will be invited for submission to journals.

All papers will be reviewed by the Program Committee on the basis of technical quality, relevance to BESC 2026, originality, significance and clarity.

Please note:

• Authors must use Springer LNCS/LNAI manuscript submission guidelines and formatting template for their submissions and each paper must be at least 6 pages and no longer than 16 pages in length (including references).
• All papers must be submitted electronically through the paper submission system in PDF format only.
• Paper review will be double-blind, and submissions not properly anonymized will be desk-rejected without review.
• Submitted papers must not substantially overlap with papers that have been published or that are simultaneously submitted to a journal or a conference with proceedings.
• Papers must be clearly submitted in English and will be selected based on their originality, timeliness, significance, relevance, and clarity of presentation.
• Submission of a paper should be regarded as a commitment that, should the paper be accepted, at least one of the authors will register and attend the conference to present the work.
• Accepted papers will be included in the proceedings of BESC 2026 and indexed by EI Compendex, ISI, Scopus, DBLP, ACM Digital Library, Google Scholar and other A&I services.
• Top quality papers after presented in the conference will be selected for extension and publication in several special issues of international journals (TBC), including:
  • IEEE Transactions on Computational Social Systems (IEEE)
  • CCF Transactions on Pervasive Computing and Interaction (Springer)
  • EURASIP Journal on Image and Video Processing (Springer)
  • World Wide Web Journal (Springer)
  • Social Network Analysis and Mining (Springer)
  • Human-Centric Intelligent Systems (Springer)
  • Natural Language Processing (Elsevier)
  • Health Information Science and Systems (Springer)
  • Web Intelligence (IOS Press)
• Papers that are substantially or entirely generated by generative AI tools are not permitted. The use of generative AI as an assistive tool (e.g., for language editing) is allowed, provided that such use is clearly and explicitly disclosed in the paper. Authors remain fully responsible for the content, originality, and integrity of their submissions.

Contact

• Dr. Zhangkai Wu, Macquarie University, Australia (zhangkai.wu[at]mq.edu.au)
• Dr. En Yu, University of Technology Sydney, Australia
• Dr. Zhihao Hao, University of Macau, Macau SAR, China
• Yongmin Yoo, Macquarie University, Australia
• Dr. Hengyu Liu, Aalborg University, Denmark
• Dr. Zhihong Cui, Oslo University, Norway