Visualizationary: Automating Design Feedback for Visualization Designers using LLMs

Interactive visualization editors empower people to author visualizations without writing code, but do not guide them in the art and craft of effective visual communication. In this paper, we explore the potential for using an off-the-shelf Large Language Model (LLM) to provide actionable and customized feedback to visualization designers. Our implementation, called VISUALIZATIONARY, showcases how ChatGPT can be used in this manner using two components: a preamble of visualization design guidelines and a suite of perceptual filters extracting salient metrics from a visualization image. We present findings from a longitudinal user study involving 13 visualization designers - 6 novices, 4 intermediate ones, and 3 experts - authoring a new visualization from scratch over the course of several days. Our results indicate that providing guidance in natural language using an LLM can aid even seasoned designers in refining their visualizations. All supplemental materials accompanying this paper are available at https://osf.io/v7hu8.
View on arXiv