Large Language Models (LLMs) have demonstrated remarkable versatility in visualization authoring, but often generate suboptimal designs that are invalid or fail to adhere to design guidelines for effective visualization. We present Bavisitter, a natural language interface that integrates established visualization design guidelines into LLMs. Based on our survey on the design issues in LLM-generated visualizations, Bavisitter monitors the generated visualizations during a visualization authoring dialogue to detect an issue. When an issue is detected, it intervenes in the dialogue, suggesting possible solutions to the issue by modifying the prompts. We also demonstrate two use cases where Bavisitter detects and resolves design issues from the actual LLM-generated visualizations.
As visualization literacy and its implications gain prominence, we need effective methods to prepare students for the variety of visualizations in an increasingly data-driven world. Recently, the potential of comics has been recognized in various data visualization contexts, including educational settings. We describe the development of a workshop in which we use our "comic construction kit" as a tool for students to understand various data visualization techniques through an interactive creative approach of creating explanatory comics. We report on our insights from holding eight workshops with high school students and teachers, university students, and lecturers, aiming to enhance the landscape of handson visualization activities that can enrich the visualization classroom. The comic construction kit and all supplemental materials are open source under a CC-BY license and available at https://fhstp.github.io/comixplain/vis4schools.html.
Visualizing high dimensional data is challenging, since any dimensionality reduction technique will distort distances. A classic method in cartography-Tissot's Indicatrix, specific to sphere-to-plane maps-visualizes distortion using ellipses. Inspired by this idea, we describe the hypertrix: a method for representing distortions that occur when data is projected from arbitrarily high dimensions onto a 2D plane. We demonstrate our technique through synthetic and real-world datasets, and describe how this indicatrix can guide interpretations of nonlinear dimensionality reduction.
Millions of runners rely on smart watches that display running-related metrics such as pace, heart rate and distance for training and racing — mostly with text and numbers. Although research tells us that visualizations are a good alternative to text on smart watches, we know little about how visualizations can help in realistic running scenarios. We conducted a study in which 20 runners completed running-related tasks on an outdoor track using both text and visualizations. Our results show that runners are 1.5 to 8 times faster in completing those tasks with visualizations than with text, prefer visualizations to text, and would use such visualizations while running — if available on their smart watch.
Augmented reality (AR) area labels can visualize real world regions with arbitrary boundaries and show invisible objects or features. But environment conditions such as lighting and clutter can decrease fixed or passive label visibility, and labels that have high opacity levels can occlude crucial details in the environment. We design and evaluate active AR area label visualization modes to enhance visibility across real-life environments, while still retaining environment details within the label. For this, we define a distant characteristic color from the environment in perceptual CIELAB space, then introduce spatial variations among label pixel colors based on the underlying environment variation. In a user study with 18 participants, we found that our active label visualization modes can be comparable in visibility to a fixed green baseline by Gabbard et al., and can outperform it with added spatial variation in cluttered environments, across varying levels of lighting (e.g., nighttime), and in environments with colors similar to the fixed baseline color.
