Accepted Special Sessions

List of Accepted Special Sessions

  • ESKM-SS1: ICT Systems to Enhance the Social Good
  • ESKM-SS2: Data Science in the Humanities and Social Sciences
  • ESKM-SS3: Advanced Remote Sensing for Coastal Area Monitoring, Mapping, and Sustainable Management
  • LTLE-SS1: Artificial Intelligence and Intelligent Learning Systems in Higher Education
  • DSIR-SS1: Institutional Research in universities to encourage students to qualify for the national examinations
  • DSIR-SS2: Data-Driven Educational Improvement and the Development of Educators’ Digital Competence
  • DSIR-SS3: Research on Student Support at Universities, Including Dropout Prediction and Prevention
  • DSIR-SS4: Institutional Research and Learning Analytics in Healthcare Professional Education: Toward a Next-Generation of Education
  • DSIR-SS5: Potential of Artificial Intelligence Models to Enhance University Research Impact
  • SCAI-SS1: Ethical and Legal Frameworks in Smart Computing and Artificial Intelligence (ELF-SCAI)
  • SCAI-SS2: AI in Safety-Critical Automotive and Medical Systems (AI-SCAM 2026)
  • SCAI-SS3: AI–Enabled Communication, Signal Processing, and Human–Machine Collaboration for Intelligent Applications
  • SCAI-SS4: Information Systems and Artificial Intelligence in Society
  • SCAI-SS5: Sixth Generation Computer Systems towards Sustainable Artificial Intelligence
  • SCAI-SS6: Smart Computing and Human-Centric AI: Innovations in Urban Systems, Health, and Resilient Infrastructure
  • SCAI-SS7: Applied Smart Computing, Interpretable and Explainable AI
  • SCAI-SS8: Evolutionary Non-Linear Feature Extraction for Temporal Grounding of Medical LLM Outputs
  • SCAI-SS9: Generative Urbanism: Empowering Civic Agency through AI-Driven Participatory Governance
  • BMOT-SS1: Business Management Systems and Strategies for Regional Economic Revitalization
  • SBIT-SS1: Application of Computer and Information Science for Business Management
  • DSTM-SS1: Decision Science on Decision Making Process
  • DSTM-SS2: Organisational Behaviour in Management
  • DSTM-SS3: Industrial Engineering and Operations Research for Energy, Natural Resource and Environmental Managements
  • CDEF-SS1: Towards Digital Twin for Economics and Finance: Foundations, Enabling Technologies, and Applications
  • CDEF-SS2: Text Analytics in Economics, Finance, and Management

IIAI AAI 2026 Special Sessions

ESKM-SS1: ICT Systems to Enhance the Social Good

Organizer: Kouichi Hirata (Kyushu Institute of Technology, Japan) and Atsuko Yamaguchi (Tokyo City University, Japan)

Abstract: We are facing many challenges locally and/or globally, such as erosion in community, aging population, climate change, pandemics, and so on. Information and communication technology (ICT) systems are expected to play many roles in our future society to tackle or solve these issues. The special session on “ICT Systems to Enhance the Social Good” is a meeting point for researchers, students, and ICT professionals interested in developing such systems to enhance the social good under such circumstances. The topics of interest in this special session include, but not limited to; ICT systems about pandemics/epidemics, diseases about crops, or zoonotic diseases; ICT systems for cyber security or privacy protection.

ESKM-SS2: Data Science in the Humanities and Social Sciences

Organizer: Daisuke Ikeda (Kyushu University, Japan)

Abstract: The advancement of informatics has significantly enhanced data collection and analysis techniques, enabling the processing of large-scale datasets and the quantitative analysis of complex knowledge structures that were previously difficult to handle. These technological developments have expanded the scope of research methodologies that can be applied in the humanities and social sciences, allowing for new data-driven approaches. Despite this progress, the humanities and social sciences have traditionally relied on specialized domain knowledge and unique analytical frameworks, which have often created barriers to interdisciplinary collaboration. As a result, while the application of data science techniques in these fields has been increasing, their integration into mainstream research remains limited. To advance interdisciplinary research, it is essential to first establish a platform for sharing knowledge and insights across these domains. This special session aims to provide a platform for sharing research that integrates data science techniques with the humanities and social sciences. In addition to studies at advanced stages, we also welcome presentations on early-stage research, research progress reports, and proposals for future studies. We invite submissions covering a wide range of topics in the humanities and social sciences. Research utilizing techniques such as machine learning, data mining, natural language processing, network analysis, image processing, and multiple regression analysis,  among other informatics-related methodologies, is particularly encouraged.

ESKM-SS3: Advanced Remote Sensing for Coastal Area Monitoring, Mapping, and Sustainable Management

Organizer: Uzair Aslam Bhatti (Hainan University, China)

Abstract: Coastal areas are among the most dynamic and vulnerable environments on Earth, facing increasing pressure from climate change, sea-level rise, shoreline erosion, habitat degradation, urban expansion, and extreme events. Remote sensing is widely used for shoreline mapping, LiDAR-based coastal surveys, and broader coastal/ocean monitoring, making it an essential tool for understanding and managing these rapidly changing systems. This special session aims to bring together researchers, practitioners, and decision-makers working on innovative remote sensing methods for coastal area processing, analysis, and application. The session will highlight recent advances in satellite, UAV, airborne, hyperspectral, SAR, LiDAR, and multi-source data fusion approaches for coastal monitoring and environmental assessment. It will also emphasize practical solutions for ecosystem conservation, disaster risk reduction, blue carbon assessment, shoreline dynamics, and sustainable coastal planning.

LTLE-SS1: Artificial Intelligence and Intelligent Learning Systems in Higher Education

Organizer: Phan Nhu Quynh (Vietnam National University, Vietnam)

Abstract: Artificial intelligence (AI) is rapidly transforming higher education by enabling intelligent learning environments, adaptive educational systems, and data-driven decision-making in teaching and academic management. Technologies such as generative AI, intelligent tutoring systems, and learning analytics are creating new opportunities to personalize learning experiences and enhance student engagement. This special session explores recent advances in AI-enabled learning technologies and intelligent educational systems in universities. It aims to provide an interdisciplinary forum for researchers and practitioners in information systems, educational technology, computer science, and management science to discuss innovative approaches to AI-supported teaching, learning, and academic administration. The session welcomes theoretical, empirical, and applied studies on AI in higher education, particularly research on learning analytics, intelligent educational platforms, and digital transformation in universities. While global contributions are encouraged, the session particularly welcomes studies from Asia, including Vietnam, Korea, and other ASEAN countries, where universities are actively adopting AI technologies to advance digital transformation and intelligent learning ecosystems. Topics include, but are not limited to:
1. Artificial Intelligence in Higher Education
2. Generative AI in Teaching and Learning
3. Intelligent Tutoring Systems and Adaptive Learning
4. Learning Analytics and Student Performance
5. AI-supported Curriculum Design
6. ChatGPT and Large Language Models in Education
7. AI Ethics and Responsible AI in Education
8. AI-driven Educational Platforms
9. Data-driven Academic Management
10. Smart Universities and Digital Transformation

DSIR-SS1: Institutional Research in universities to encourage students to qualify for the national examinations

Organizer: Kenjiro Sakaki (Tenshi College, Japan) and Kunihiko Takamatsu (Institute of Science Tokyo, Japan)

Abstract:In 2012, the Ministry of Education, Culture, Sports, Science, and Technology (MEXT) proposed the establishment of Institutional Research (IR) in Japanese universities. Most universities have since launched this department. One of the objectives of the IR department is to reform the education system in order to advance higher education. Universities can be classified into two categories. The first type is designed to enable students to qualify for the national examination. The second type includes the universities excluding those under the first type. We can refer to the former as a national license-type university. MEXT promotes higher education reforms in universities. However, the curriculum of the national license-type university has to conform with the rules in order to obtain a qualification for the national examination from the corresponding ministry. Hence, there should be a difference between the IR in a license-type university and a non-license-type university. We will discuss the differences and similarities between the IR in license and non-license-type universities.

DSIR-SS2: Data-Driven Educational Improvement and the Development of Educators’ Digital Competence

Organizer: Yuji Kobayashi (Kyushu Institute of Technology, Japan)

Abstract: As digitally enriched learning environments become standard across higher education, online and hybrid teaching have become routine practices. Learning management systems (LMS), video conferencing platforms, generative artificial intelligence, and other educational technologies are widely implemented. However, their effectiveness depends not merely on infrastructure, but on the digital competence of educators who design, implement, and evaluate learning experiences. Technological provision alone does not guarantee improvement. Educators must select appropriate digital tools, integrate them into instructional design, interpret learning data, and translate evidence into effective pedagogical practice. Therefore, developing educators’ digital competence is a critical priority for sustainable reform in higher education. This special session invites theoretical frameworks and empirical studies connecting competence development with data-driven educational improvement. We welcome research linking digital competence with learning analytics, instructional design, and institutional research, as well as contributions extending these approaches beyond higher education, including vocational education and sports coaching. Relevant topics include competence frameworks and assessment methods; faculty development initiatives based on digital competence evaluation; visualization of digital teaching practices using syllabus and public data; instructional improvement grounded in LMS log and course data; integrated quantitative and qualitative analyses; collaborative models involving Student Consulting on Teaching (SCOT) and teaching assistants; AI-supported teaching consultation systems; AI agents for career guidance and educational enhancement; and connections between data-informed practice, quality assurance, and institutional governance.
This session examines digital transformation as a collaborative, evidence-based process for sustainable educational improvement.

DSIR-SS3: Research on Student Support at Universities, Including Dropout Prediction and Prevention

Organizer: Naruhiko Shiratori (Tokyo City University, Japan)

Abstract: In higher education, predicting and preventing student dropout is a critical issue. However, effective student support strategies extend beyond simply reducing dropout rates. Providing robust academic support, identifying at-risk students at an early stage, and implementing data-informed interventions are all vital for enhancing student success and improving academic outcomes.
This special session invites research that addresses not only dropout prediction and prevention, but also broader strategies aimed at fostering student success. Possible topics include, but are not limited to, the use of learning analytics to identify at-risk students, the design and evaluation of targeted support programs, the development and assessment of institutional policies to promote student achievement, and cross-institutional analyses that inform evidence-based policy-making.
We welcome a wide range of methodologies and levels of analysis, from micro-level approaches (e.g., learning analytics and early warning systems at the individual student level) to macro-level perspectives (e.g., departmental, institutional, or nationwide strategies). Through this session, we aim to advance discussions on data-driven approaches that empower Institutional Research (IR) professionals and decision-makers, ultimately contributing to greater student success and improved retention in higher education.

DSIR-SS4: Institutional Research and Learning Analytics in Healthcare Professional Education: Toward a Next-Generation of Education

Organizer: Yoshikazu Asada (Jichi Medical University, Japan)

Abstract: Recently, several important issues have emerged in healthcare professional education. The first is generative AI. Since the public release of ChatGPT in 2022, educational practices have been significantly influenced. For example, written homework and assignments can now be easily completed using generative AI, raising concerns about their validity as assessment tools. The advantages and disadvantages of generative AI in education should therefore be examined based on appropriate educational evidence. The second issue concerns the new Model Core Curriculum (MCC). In 2022, the MCCs for medical, pharmaceutical, and dental education were revised. In 2024, the nursing MCC was also updated, introducing a common competency framework for healthcare professionals. As shared competencies are now being adopted across disciplines, comparative analysis of curricula among different domains will become increasingly important. The third issue is the MDASH (Mathematics, Data Science and AI Smart Higher Education) program. This program has been widely implemented not only in healthcare professional education but also in other academic fields. Evaluating the effectiveness of its integration—particularly in relation to ICT-related knowledge and skills—will be essential. In this symposium, we will discuss these emerging trends and issues in healthcare professional education, while also extending the discussion beyond these specific topics.

DSIR-SS5: Potential of Artificial Intelligence Models to Enhance University Research Impact

Organizer: Michiko Yasukawa (Gunma University, Japan)

Abstract: Recent advancements in generative artificial intelligence (AI) have significantly transformed the landscape of scientific inquiry, enabling researchers in fields such as mathematics, chemistry, and physics to integrate sophisticated AI models into their discovery processes. However, from the perspective of Institutional Research (IR), the systematic integration of advanced AI to analyze research information remains insufficiently explored. This special session aims to discuss the potential of state-of-the-art generative AI models to increase the impact of university research. We will focus not only on individual research promotion but also on how AI can support institutional-level strategies, such as identifying emerging research trends, optimizing research grant applications, and improving the efficiency of peer-review or screening processes. This session is designed to invite researchers, university administrators, and IR practitioners to share theoretical frameworks, empirical studies, and case reports on AI-driven research information analysis. Relevant topics include, but are not limited to: Strategic use of Large Language Models (LLMs) in research grant writing and evaluation; Automated systems for research collaboration matching and interdisciplinary development; Integration of generative AI with bibliometrics and altmetrics for institutional strategy; AI-supported research profiling and impact prediction. In this session, we encourage participants to explore how universities can strategically adopt AI to foster a sustainable and innovative research environment for the future.

SCAI-SS1: Ethical and Legal Frameworks in Smart Computing and Artificial Intelligence (ELF-SCAI)

Organizer: Gaianu Mihail (West University of Timisoara, Romania) and Stanila Laura (West University of Timisoara, Romania)

Abstract: As Smart Computing and Artificial Intelligence (AI) become deeply integrated into critical infrastructure, autonomous systems, and daily life, the intersection of technological capability and legal responsibility has become a critical area of research. This special session aims to bridge the gap between advanced applied informatics and legal/ethical frameworks. We invite researchers and practitioners to discuss how to integrate “Ethics by Design” and legal compliance directly into smart computing architectures. The session will focus on the technical challenges of implementing regulatory requirements (such as the EU AI Act, GDPR, and liability laws) within AI algorithms and smart environments. We welcome papers addressing the translation of abstract legal concepts (fairness, accountability, transparency) into computable constraints and verifiable system behaviors.

SCAI-SS2: AI in Safety-Critical Automotive and Medical Systems (AI-SCAM 2026)

Organizer: Gaianu Mihail (West University of Timisoara, Romania)

Abstract: The rapid advancement of Artificial Intelligence (AI) has become the cornerstone of innovation in both the Automotive (Industry 4.0/5.0) and Medical (Healthcare 4.0) sectors. While these domains appear distinct, they share a critical operational constraint: they are safety-critical environments where AI failure is not an option. This special session aims to explore the transformative power of AI in these twin pillars of modern technology. We seek to identify common algorithmic innovations and architectural patterns—such as Edge AI, Computer Vision, and Explainable AI (XAI)—that solve complex problems in both autonomous mobility and precision medicine. By bringing together researchers from vehicle engineering and biomedical informatics, this session will foster a unique cross-pollination of ideas regarding reliability, real-time data processing, and human-centric AI design.

SCAI-SS3: AI–Enabled Communication, Signal Processing, and Human–Machine Collaboration for Intelligent Applications

Organizer: Chih-Chien Hu (Tatung University, Taiwan) and Sulin Chi (Otemon Gakuin University, Japan)

Abstract: Recent advances in artificial intelligence (AI), signal processing, and communication technologies are rapidly transforming the way humans interact with intelligent systems across diverse application domains. This special session focuses on emerging theories, methodologies, and applications that integrate AI-enabled communication, advanced signal processing, and human–machine collaboration to support intelligent, context-aware systems, and STEM education. The session aims to highlight interdisciplinary approaches that enhance information interpretation, multimodal interaction, and decision-making in complex environments. Key topics include AI-driven signal analysis, multimodal communication and perception, intelligent sensing and pattern recognition, human–AI cooperative frameworks, and adaptive interaction models for cyber-physical systems. Special emphasis is placed on enabling seamless collaboration between humans and intelligent machines through robust communication channels, explainable AI, and user-centered system design. Applications span smart healthcare, assistive technologies, robotics, immersive learning environments, and next-generation human–computer interaction. This session provides a platform for researchers and practitioners to present innovative solutions, share empirical findings, and discuss future research directions. By fostering interdisciplinary collaboration, the session seeks to advance the development of intelligent systems that not only process signals and communicate effectively but also collaborate with humans to enhance performance, accessibility, and user experience in real-world applications.

SCAI-SS4:  Information Systems and Artificial Intelligence in Society

Organizer: Kazunori Iwata (Aichi University, Japan) and Nobuhiro Ito (Aichi Institute of Technology, Japan)

Abstract: This special session focuses on research on Artificial Intelligence (AI) and information systems for societal applications. Contributions are expected to include evaluation results obtained through deployment in real-world environments or simulation fields.
In recent years, numerous information systems and AI technologies have been developed for real-world societal use. These technologies are widely embedded in social infrastructures and human daily life. Behind these developments, innovative and intelligent technologies continue to emerge, enabling the design and implementation of advanced software systems.
Accordingly, this session welcomes research contributions in the following topics, including but not limited to:
(1) Multi-agent systems;
(2) Multi-agent simulation technologies and coordination mechanisms;
(3) Intelligent applications and societal data analysis;
(4) Intelligent educational systems;
(5) Hybrid sensor systems leveraging AI.
In addition, this session focuses on research related to RoboCup Rescue Simulation (RRS). The purpose of the RRS league is to develop simulation infrastructures that emulate realistic disaster phenomena, as well as intelligent agents and robots that represent the principal actors in disaster response scenarios.

SCAI-SS5: Sixth Generation Computer Systems towards Sustainable Artificial Intelligence

Organizer: Naoki Sawahashi (University of Florida, USA) and Jose Principe (University of Florida, USA)

Abstract: An artificial neural network (ANN) coupled with graphics processing units (GPUs) is currently the predominant form of artificial intelligence (AI). This combination achieves remarkable scalability and universality, as demonstrated by the rapid adoption of large language models across many fields (e.g., scientific research, education, medicine). However, its skyrocketing energy costs are casting a shadow over sustainability and raising environmental concerns, especially in the development (i.e., training) of such a model. ANNs generally require floating-point multiplications over enormous training datasets. Several techniques and models improve energy efficiency by reducing arithmetic operations on real numbers, such as weight quantization, weightless neural models, logic gate networks, and automatons. Alternatively, using analytic solutions (e.g., kernel-based methods) can lower the number of training samples required. Nonetheless, these alternatives are currently less scalable than ANNs and require further research. This special session aims to explore methodologies and platforms for ultra‑low‑power machine learning, covering computational models (i.e., software) and hardware engineering with efficiency in mind (with or without ANNs). Topics of interest include:

  • Hardware accelerators for Edge ML/AI of Things (AIoT)
  • Neuromorphic/bio‑inspired computing (e.g., spike‑based computing)
  • Kernel methods in machine learning
  • Cellular automata
  • Automata theory (Tsetlin machines)
  • Tiny machine learning (TinyML)
  • Analog computers and physics-driven ML (e.g., memristors, field‑programmable analog arrays)

We welcome anyone interested in discussing learning theories and hardware platforms for sustainable machine learning, including but not limited to researchers, engineers, commercial entities, educators, and students.

SCAI-SS6: Smart Computing and Human-Centric AI: Innovations in Urban Systems, Health, and Resilient Infrastructure

Organizer: Huong Le (New Jersey Institute of Technology, USA)

Abstract: This special session explores the intersection of smart computing and artificial intelligence in shaping the future of interconnected environments. As urban and healthcare landscapes become increasingly data-rich, there is a critical need for robust, scalable, and explainable AI frameworks that enhance human well-being and infrastructural resilience. We invite original research contributions that bridge advanced machine learning methods—including deep generative models and hybrid AI—with practical applications in smart city governance and public health. Key areas of interest include AI-driven video analytics for traffic safety and autonomous systems, predictive modeling for next-generation urban digital twins, and smart health ecosystems featuring digital assistants and advanced medical imaging. Furthermore, the session emphasizes the importance of human-AI co-creative workflows, empowering policymakers, architects, urban planners, and healthcare providers to make real-time, data-informed decisions. We encourage submissions addressing the challenges of energy transition, infrastructure protection, and socio-technical systems analysis. By fostering an interdisciplinary dialogue between smart computing, spatial data analytics, and participatory design, this session aims to highlight innovations that support equitable, sustainable, and secure societal transformation. We welcome theoretical foundations, practical implementations, and case studies that demonstrate the transformative power of AI in the built environment and beyond.

SCAI-SS7: Applied Smart Computing, Interpretable and Explainable AI

Organizer: Takafumi Nakanishi (Tokyo University of Technology, Japan)

Abstract: This special session focuses on integrating smart computing technologies with explainable artificial intelligence (XAI) to realize reliable, human-centered, application-oriented AI systems. As AI becomes deeply embedded in critical domains such as healthcare, finance, manufacturing, public policy, sports, wellness, and creative industries, the demand for transparency, accountability, and operational reliability is significantly increasing. Smart computing refers to intelligent systems that combine data analytics, machine learning, optimization, edge/cloud computing, and adaptive decision-making to solve complex real-world challenges efficiently. However, performance alone is insufficient. Modern AI systems must also provide understandable reasoning processes, support domain experts’ decision-making, and comply with emerging regulatory and ethical frameworks.

SCAI-SS8: Evolutionary Non-Linear Feature Extraction for Temporal Grounding of Medical LLM Outputs

Organizer: Chaitanya Kumar Mankala (Villanova University, USA)

Abstract: Large Language Models (LLMs), such as Med-PaLM, excel at biomedical knowledge retrieval but struggle with grounding outputs in dynamic, non-linear patient data (e.g., vital sign trends, lab trajectories). This paper introduces the Two-Stage Validation Funnel, a novel serverless architectural framework designed to enhance clinical safety and grounding. In Stage 1 (Feature Extraction), an Evolutionary Artificial Neuroidal Network (EANN), optimized for non-linear temporal modeling using five adjustable parameters, processes raw clinical time-series data to extract robust, low-dimensional feature vectors. In Stage 2 (Validation), these EANN features are leveraged by lightweight, specialized Deep Learning (DL) and Machine Learning (ML) models to generate real-time contradiction flags and confidence scores for LLM-generated diagnoses. Implemented within a scalable, cost-efficient AWS serverless architecture (Lambda, Batch), this funnel provides vital temporal grounding, enhancing the safety and clinical utility of LLMs in real-time healthcare applications.

SCAI-SS9: Generative Urbanism: Empowering Civic Agency through AI-Driven Participatory Governance

Organizer: Kamran Soomro (University of the West of England, Bristol, United Kingdom)

Abstract: This special session examines the evolution of participatory urban governance through the lens of Generative Artificial Intelligence (GenAI), addressing what recent scholarship identifies as the ‘participation paradox’—a disconnect between high digital readiness and low civic trust in automated processes (Al-Enabled Participatory Urban Planning, 2026). While smart city initiatives have traditionally prioritised technocentric efficiency, this session shifts focus towards citizen empowerment and inclusive co-design. The integration of GenAI tools, such as multimodal LLMs and immersive digital twins, presents a unique opportunity to bridge the gap between decision-makers and the public. We specifically explore how GenAI can empower residents by translating complex technical planning data into intuitive visual and linguistic formats, enabling meaningful engagement in urban simulations. Contributions are invited on topics including synthetic inhabitant models for testing inclusive policies, the mitigation of ‘black box’ institutional routines, and frameworks for ‘trustworthy AI’ that prioritise public sovereignty over administrative automation. By investigating the intersection of agentic AI and democratic urbanism, this session seeks to define new methodologies for placing citizens at the heart of the generative planning process, ensuring that technological transitions foster genuine social resilience and democratic accountability.

BMOT-SS1: Business Management Systems and Strategies for Regional Economic Revitalization

Organizer: Hidekazu Iwamoto (Josai International University, Japan)

Abstract: This special session offers business management systems and strategies for the revitalization of regional economies. Based on all aspects (theories, applications, and tools) of business management systems and strategies, the special session will discuss the practical challenges associated with this topic.

SBIT-SS1: Application of Computer and Information Science for Business Management

Organizer: Yukihiro Shintani (Chiba Institute of Technology, Japan)

Abstract: In the rapidly evolving business landscape, the role of computer and information science has become increasingly critical. The ability to effectively manage and use data is central to business strategy and operations. This special session will explore the application of computer and information science to business management. It seeks to uncover how the principles and technologies of information science can optimize business processes, improve decision making, and foster innovation. By bridging the gap between theoretical knowledge and practical application, this session aims to provide insights into the effective use of information technologies in the business world. Topics of interest include but are not limited to:

  • Business Intelligence and Analytics
  • Web3 Technology for Business Management
  • Marketing Analytics and Consumer Behavior Analysis
  • Information Systems Strategy and Governance
  • Risk Management and Compliance Technologies
  • Privacy, Security and Ethics in Business Information Systems
  • Innovation Management and Digital Product Development
  • Artificial Intelligence and Machine Learning for Business Solutions

DSTM-SS1: Decision Science on Decision Making Process

Organizer: Katsuki Yasuoka, Eriko Musashi (Advanced Institute of Industrial Technology, Japan)

Abstract: Research on the decision-making process explores how individuals or groups make choices. It examines factors influencing decisions, such as cognitive biases, emotions, and social influences. Studies often analyze decision-making models, strategies, and their outcomes. Understanding this process can lead to insights into improving decision-making effectiveness in various contexts, including business, psychology, and public policy. This special session focuses on the decision-making process for human activity. Based on several theories, this session aims to discuss various topics about decision making.

DSTM-SS2: Organisational Behaviour in Management

Organizer: Morihiko Ikemizu (Advanced Institute of Industrial Technology, Japan)

Abstract: Organizational behavior theory is an academic field that studies the behavior and interactions of individuals and groups within organizations, and the factors that influence them. This field seeks to better understand how people behave in organizations, why they behave in certain ways, and the impact this has on the organization as a whole. This session will specifically address effective leadership, teamwork, and motivation within organizations.

DSTM-SS3: Industrial Engineering and Operations Research for Energy, Natural Resource and Environmental Managements

Organizer: Ryuta Takashima and Kazuya Ito (Tokyo University of Science, Japan)

Abstract: Firms in the energy and natural resource sectors face growing risks and uncertainties, including prices volatility, rapidly evolving market conditions, supply chain disruptions, and increasingly stringent regulatory frameworks. In addition, the global push toward decarbonization and heightened concerns over climate change are fundamentally reshaping the environment in which these firms operate. Environmental policies and regulations are no longer peripheral considerations but central factors influencing long-term investment, operational strategies, and system resilience. Addressing these complicated challenges requires rigorous analytical approaches that go beyond conventional planning methods. Industrial engineering and operations research provide powerful frameworks for modeling uncertainty, evaluating trade-offs, and designing robust strategies in complex socio-economic and technological systems. These methodologies enable firms and policymakers to make informed decisions that balance economic performance, environmental responsibility, and system reliability. This special session highlights recent advances in the application of industrial engineering and operations research to energy, natural resource, and environmental management. The session will include research on: (1) investment in power generation and transmission under uncertainty; (2) risk management in power purchase agreements; (3) decision-making in sustainable forest management; (4) optimization models for hydrogen supply networks and production technology deployment; and (5) energy production planning models integrating resource supply–demand network optimization with decarbonization technology selection. By examining these topics, the session aims to demonstrate how quantitative decision-making methods can support sustainable and resilient management practices across energy and natural resource systems.

CDEF-SS1:  Towards Digital Twin for Economics and Finance: Foundations, Enabling Technologies, and Applications

Organizer: Ryuji Hashimoto (The University of Tokyo, Simulacra Inc., Japan) and Takanobu Mizuta (SPARX Asset Management Co.,Ltd., Japan)

Abstract: Recent advances in artificial intelligence (AI), data infrastructures, and computational modeling are creating new opportunities to build digital twins of economic and financial systems. This special session focuses on both the construction and utilization of digital twins for economics and finance, and broadly welcomes enabling technologies and methodological innovations that contribute to this vision.
On the construction side, we invite research on realistic modeling of individual behavior, such as behavioral finance, learning agents, personalization, large language models, and agentic AI, as well as faithful representations of social and market structures through agent-based modeling, knowledge extraction from data, calibration and optimization, synthetic data generation, and high-fidelity simulation environments. On the utilization side, we welcome contributions exploring how digital twins can support decision-making at multiple levels, including individual-level decision support (e.g., advisory systems and risk management) and collective-level governance and policy-making, such as institutional design, policy evaluation, stress testing, and regulation of AI-mediated markets. We encourage diverse approaches and interdisciplinary perspectives that advance the development and practical deployment of digital twins for economics and finance.

CDEF-SS2: Text Analytics in Economics, Finance, and Management

Organizer: Masahiro Kato (Mizuho–DL Financial Technology, Japan), Kei Nakagawa (Osaka Metropolitan University, Japan), Hiroki Sakaji (Hokkaido University, Japan)

Abstract: In recent years, advances in natural language processing (NLP), text mining, and large language models (LLMs) have substantially expanded the role of unstructured information in economics, finance, and management. A broad range of real-world signals—central bank communications, regulatory documents, corporate disclosures, earnings call transcripts, analyst reports, news, and social media—shape expectations, beliefs, and behavior. These textual sources often capture uncertainty, narratives, sentiment, and organizational intent that cannot be fully represented by conventional numerical data (e.g., prices, volumes, and accounting variables).
At the same time, domain-specific challenges remain. Economic and financial texts are highly context- and time-dependent, rich in jargon, and tightly linked to institutions and regulations. Evaluation is also non-trivial: beyond predictive accuracy, practical deployments require robustness, interpretability, auditability, and careful risk management (including model risk and hallucination risk for generative systems). As a result, there is a strong need for a dedicated forum that brings together researchers and practitioners to discuss methods, benchmarks, and practical deployments tailored to economics, finance, and management.
Therefore, we propose a specialized session, “Text Analytics in Economics, Finance, and Management,” to broadly recruit and disseminate practical and scientific research at the intersection of text analytics and socio-economic decision making. In this session, we will actively encourage presentations from industry researchers and practitioners, as well as academic researchers, to facilitate knowledge transfer and collaboration across sectors.