data visualization

Decision support in visualization research lacks systematic characterization of decision-context frameworks, and existing task models fail to guide design for real-world decision scenarios. Method: We propose a structured decision-problem analysis framework that, for the first time, decomposes decision problems into three core attributes—data, user, and task context—and explicitly articulates their constraints and implications for visual encoding and interaction design. Grounded in task-modeling principles and visualization design theory, we develop an operational feature-description system for decision problems and validate it through multi-case analysis. Contribution/Results: The framework addresses the critical gap in traditional task models—neglect of decision context—and provides the first systematic theoretical tool for decision-oriented visualization research. It reveals limitations in current design practices and identifies concrete pathways to enhance decision-support efficacy in authentic settings.

Static visual explanations—such as heatmaps, concept-based attributions, and prototype-based methods—suffer from information overload, poor semantic-pixel alignment, and limited exploratory capability. This paper presents the first systematic investigation of interactive mechanisms across these three dominant computer vision explanation paradigms. Through a 24-participant user study on fine-grained bird recognition, we employ mixed qualitative and quantitative analysis to evaluate how dynamic masking, concept filtering, and prototype navigation impact information acquisition efficiency, alignment accuracy, and cognitive expansion. We derive three human-AI collaborative explanation design principles: adaptive default views, decoupled input controls, and constrained output spaces; identify novel challenges—including interaction overload and intent misalignment; and formulate seven actionable, implementation-ready guidelines for interactive explainable AI. This work has been accepted to CHI ’25.

Communication barriers between data scientists and domain experts arise from oversimplified, accuracy-centric model performance reporting, hindering shared understanding of model limitations and contextual applicability. Method: We propose a visualization-mediated model explanation framework grounded in human-computer interaction principles, participatory design, and visual narrative techniques. This yields the first domain-expert-oriented model communication guideline—emphasizing risk, trade-offs, and situational appropriateness rather than isolated metrics like accuracy. An iterative empirical study was conducted using regression models, incorporating structured expert feedback for evaluation. Contribution/Results: The framework significantly improves domain experts’ ability to identify model limitations, recognize inherent trade-offs, and proactively make context-driven adoption decisions. Its core innovation lies in repositioning visualization as an interdisciplinary consensus-building medium—shifting the paradigm from “metric reporting” to “collaborative understanding.”

Visualization practitioners often lack formal training, resulting in significant gaps in design knowledge. Method: This paper presents the first systematic evaluation of large language models (LLMs) for visualization design consultation, employing a dual-path approach: quantitative analysis (multidimensional comparison of ChatGPT and expert responses from VisGuides) and qualitative analysis (double-blind user studies, content coding, and human-AI co-feedback analysis). Results: While ChatGPT rapidly generates diverse design alternatives, it substantially underperforms human experts in deep contextual understanding, visual intent inference, and support for nonlinear interactions. The study proposes a novel “context-enhanced + interaction-guided” paradigm tailored to design feedback, establishing both theoretical foundations and a practical framework for developing trustworthy LLM-assisted visualization design systems.

Interactive visualization editors lack real-time guidance grounded in visual communication principles, limiting design quality. To address this, we propose the first end-to-end feedback framework integrating large language models (LLMs), domain-specific visualization design guidelines, and image-aware perceptual filters to generate actionable, personalized natural language design recommendations. Our method injects structured domain knowledge via prompt engineering and leverages perceptual filters to extract salient visual metrics—enhancing LLM reasoning reliability and grounding suggestions in perceptual evidence. In a longitudinal multi-day study with 13 designers spanning novice to expert levels, our system significantly improved iterative refinement quality and depth of design reflection, receiving high usability ratings. This work provides the first empirical validation of LLMs’ effectiveness in delivering experience-agnostic, principle-based feedback for visualization design—establishing a novel paradigm for intelligent, adaptive design assistance tools.

This study investigates why novice learners often overlook well-designed visual scaffolds in multi-view programming visualization tools. Employing eye-tracking, think-aloud protocols, and reflective interviews alongside Python Tutor and multi-representational probe instruments, the research examines cognitive and affective engagement among undergraduate students as they simultaneously interact with code, memory, and metaphorical views. Findings reveal three key factors shaping selective engagement: agency, representational congruence, and disciplinary legitimacy, underscoring the critical role of affective and social dimensions in tool adoption. Results indicate that nearly half of participants’ time was spent exclusively on code, with less-experienced learners engaging even less with metaphorical representations. The study advocates positioning visualizations primarily as validation aids, supporting switchable levels of abstraction, and enhancing their academic legitimacy to foster effective use.

This study investigates the discrepancies between large language models (LLMs) and human cognition in high-level chart understanding, with a focus on interpreting designer intent and extracting complex data patterns. Through qualitative user studies, it systematically compares the higher-order interpretation strategies employed by humans and LLMs on line charts, bar charts, and scatter plots, while analyzing LLM outputs and reasoning pathways under three distinct prompting conditions. The work reveals, for the first time, that LLMs consistently adopt a structured enumeration strategy rather than constructing coherent trend-based narratives, and their explanatory patterns remain remarkably stable across different prompts. In contrast, humans demonstrate a superior ability to synthesize holistic, narrative-driven interpretations. These findings highlight fundamental mechanistic limitations of LLMs in visual reasoning and offer critical insights for future model design.

Existing AI-assisted visualization tools struggle to accurately align user intent with visual representation and face unique challenges in practice. This study addresses these limitations through an empirical investigation involving 16 interdisciplinary participants who completed visualization tasks using a natural language–driven vibe coding tool. Combining task-based experiments with semi-structured interviews, the work systematically characterizes user behavior patterns during prompt formulation, result evaluation, and iterative refinement. The findings reveal distinct practices in visualization contexts that diverge from general-purpose programming, identifying key barriers that impede effective output generation. These insights provide both theoretical grounding and practical guidance for the design of next-generation AI-powered visualization systems.

This study addresses the cognitive inefficiency of traditional normal distribution visualizations in probability comparison tasks and the lack of a systematic account linking design choices to user cognition. For the first time, it systematically integrates affordance theory from psychology into the design of static probabilistic visualizations. By analyzing the affordance characteristics of existing normal density plots, the authors propose a novel visualization form—the Croissant Chart. Combining cognitive psychology theory, visualization design principles, and a preregistered user study (N = 808), they demonstrate that this chart significantly improves both accuracy and response efficiency in probability comparison tasks. The work establishes an affordance-driven design methodology capable of predictably enhancing task performance.

This study addresses a critical gap in visualization research by systematically investigating the design decision-making processes behind annotations—a dimension often overlooked despite extensive focus on their visual forms. Through a two-phase qualitative study involving semi-structured interviews with ten practitioners and seven educators, the work integrates practical and pedagogical perspectives to uncover tacit expert knowledge in annotation design. The authors reconceptualize annotations not merely as static visual elements but as dynamic design activities, revealing key trade-offs among clarity, guidance, and viewer agency. Building on these insights, they formulate a set of heuristic strategies and context-sensitive judgment principles. These contributions provide both theoretical grounding and practical support for the development of visualization tools and design guidelines.