interactive dashboards

Existing visual analytics (VA) process models inadequately capture the dynamic roles and bidirectional interactions among humans, data, and models—particularly regarding explainable AI (XAI), knowledge externalization, and closed-loop feedback. To address this gap, we propose HDMI Canvas: the first VA framework centered on triadic, bidirectional human–data–model interaction, integrating descriptive and generative capabilities. Grounded in human factors engineering, XAI principles, knowledge externalization theory, and closed-loop feedback design, HDMI Canvas emphasizes co-evolution between human cognition and model outputs, enabling interdisciplinary collaboration and stakeholder engagement. Evaluated through two empirical case studies, the framework significantly enhances the systematicity of VA process design, the effectiveness of user-centered practices, and the interpretability of cross-domain communication. HDMI Canvas thus advances a new paradigm for human–AI symbiotic intelligent analytics. (136 words)

Existing visualization tools commonly embed data loading and transformation logic within visualization components, leading to redundant development efforts, high user learning costs, and difficulties in cross-tool data interoperability. Method: This paper proposes a modular architecture that systematically decouples data processing from visualization logic for the first time. It defines standardized data interfaces and a dynamic integration mechanism, implemented as a web-based prototype supporting bidirectional data flow and parallel collaboration across heterogeneous tools while preserving their autonomy. Contribution/Results: The architecture establishes a unified data interaction layer without compromising tool independence. Empirical evaluation demonstrates significant reductions in developers’ reimplementing overhead and users’ learning curves. Moreover, it enables scalable, open, and collaborative visualization ecosystems—introducing a novel, extensible paradigm for integrated visual analytics.

This study addresses the challenge of intuitively representing complex interdependencies among simulation parameters in traditional tabular interfaces, which often lead to configuration errors and excessive cognitive load. To mitigate this, the work proposes the first application of an interactive Sankey diagram for visualizing parameter dependencies. A functional interface prototype was developed and evaluated against a conventional table-based approach using the PURE heuristic evaluation method, with a focus on user comprehension efficiency. Empirical results demonstrate that the Sankey diagram significantly reduces cognitive load by 51% and decreases interaction steps by 56%, thereby substantially enhancing the understandability and usability of configuration-intensive systems. This approach establishes a novel paradigm for visualizing parameter dependencies in complex simulation environments.

Existing visualization research predominantly focuses on *how to use* interactive features, neglecting the critical question of *how to construct* them. Method: We propose the first three-layer decoupled interaction authoring task model—intent–technique–component—derived from empirical coding and abstraction of 592 interaction units across 47 real-world applications. Contribution/Results: This model provides descriptive, evaluative, and generative capabilities, enabling the first unified formalization of interaction authoring intent, technical implementation, and component instantiation. It yields a reusable, theory-grounded classification framework that supports critical evaluation of existing visualization tools and informs the design and validation of next-generation low-code interaction authoring systems.

Business professionals—non-technical domain experts—lack appropriate tools and methodologies for effective what-if analysis (WIA), hindering data-informed decision-making. Method: We conducted a two-phase mixed-methods user study—comprising contextual interviews and in-situ task-based evaluations—to systematically characterize their analytical behaviors for the first time. Contribution/Results: Based on empirical findings, we propose three domain-grounded design principles: business-contextual data preparation, risk-aware assessment, and domain-knowledge integration. We implemented and validated these principles in an interactive visual analytics prototype. The study identifies three critical support gaps, empirically confirms that six classes of what-if techniques significantly improve decision efficiency and confidence, and yields eight actionable design guidelines for commercial business intelligence systems. This work bridges a key theoretical and practical gap in WIA research concerning non-technical users.

This study addresses the systematic challenge of integrating human-centered and machine-centered processes in visual analytics workflows by proposing an information-theoretic ontological approach. Through action research and multi-domain case studies, it demonstrates for the first time the feasibility of theory-driven optimization in real-world settings and identifies key barriers limiting its broader adoption. The work clarifies both the strengths and limitations of this approach, fosters consensus within the field, and articulates a practical roadmap to facilitate its implementation. By doing so, it provides both theoretical grounding and actionable guidance for the co-design of visual analytics systems.

This study addresses core challenges in human–data interaction in the AI era, including perceptual latency, limited scalability, outdated interaction paradigms, and insufficient reliability and interpretability of generative outputs. It systematically examines the impact of AI technologies on human–data interaction, exploration, and visualization, redefining the role of humans in intelligent analysis. Integrating insights from cognitive science, perceptual theory, and interaction design principles, the work proposes a human-centered interaction framework that synergizes large language models (LLMs), vision-language models (VLMs), and multimodal visualization techniques. Moving beyond traditional evaluation metrics focused primarily on efficiency and scalability, this research advances a cognition-driven analytical paradigm for human–AI collaboration and articulates design principles and future research directions for human-centric intelligent analytics systems in the AI era.

This study addresses the lack of reusable, cross-context data analytics infrastructure in current educational AI systems, which hinders consistent processing of heterogeneous learning interaction data. Building upon the A4L modular data architecture, the authors design and implement a domain-agnostic, highly configurable analytics pipeline that unifies the collection, processing, and analysis of multi-source educational AI interaction data. Through modular design, an extensible architecture, and cross-domain data integration techniques, the pipeline supports closed-loop personalized learning and instructional feedback. Its generalizability, scalability, and reusability are empirically validated by successfully reproducing key analytical results across three distinct educational settings, thereby providing foundational support for the evaluation and iterative improvement of educational AI systems.

To address the lack of a systematic framework for agent design in mixed-initiative visual analytics, this study proposes the first comprehensive, lifecycle-spanning six-dimensional agent design space—encompassing perception, environment understanding, action capability, communication strategy, role dynamics, and human–agent collaborative reasoning. Grounded in a systematic literature review and cross-case coding analysis of 90 visual analytics systems and 207 agents, we develop an extensible, reusable classification framework. This framework supports both design decisions for new systems and systematic positioning and evaluation of existing ones. It explicitly identifies critical research gaps—including dynamic role switching and formal modeling of collaborative reasoning—thereby providing theoretical foundations and practical guidance for agent-driven visual analytics. (136 words)

Traditional one-shot optimization approaches struggle to accurately capture decision-makers’ true preferences regarding objectives, constraints, and trade-offs, and often lack effective human-in-the-loop interaction mechanisms. This work proposes an interactive optimization agent framework powered by large language models, which simulates multi-stakeholder dialogues through role-playing. By integrating internal utility function modeling, domain-specific prompt engineering, and structured tool invocation, the framework dynamically generates, explains, and refines solutions. The study introduces a scalable and reproducible evaluation methodology, generating thousands of dialogue rounds in a school timetabling case study. Results demonstrate that the proposed customized agent converges to significantly superior solutions in fewer interaction rounds compared to general-purpose chatbots.