CatPAL: Task-Aware Learning for Categorical Palette Recommendation
Authors
Chin Tseng (University of North Carolina-Chapel Hill), Arran Zeyu Wang (University of North Carolina-Chapel Hill), Yunqi Li (University of North Carolina at Chapel Hill), Danielle Albers Szafir (University of North Carolina-Chapel Hill)
Presentation
- Session
- Great, now you scattered the data everywhere!
- Time
- Tuesday, Nov 10, 15:36 – 15:48 (US/Eastern) · session 15:00 – 16:30
- Location
- Hall Essex center
Keywords
Categorical perception, shape perception, multiclass scatterplots, visualization effectiveness, quantitative study
Abstract
Designing effective categorical palettes requires balancing a range of factors, including perceptual distinctiveness, category count, and task effectiveness. The effectiveness of categorical encodings can vary substantially depending on the target analytical tasks; however, existing recommendation tools largely ignore task context when evaluating palette quality, resulting in inconsistent performance across tasks. We synthesize findings from a series of multi-stage user studies into a unified model of task-based effectiveness for color encodings, shape encodings, and their redundant combination across category counts and seven common scatterplot tasks. Our results show that task and palette choice jointly influence perceptual accuracy: different color and shape palettes exhibit varying levels of robustness across tasks, indicating that palette effectiveness is task-dependent. We estimate task-specific perceptual strengths for 39 colors and 39 shapes using Bradley-Terry models, refined through adaptive sampling to target uncertain and task-sensitive comparisons. We further quantify cross-channel interactions using a redundant gain Delta G metric to model performance across color and shape pairings. We then train a predictive model that scores candidate palettes based on task, category count, and perceptual features. This model drives effective palette recommendations in CatPAL, a task-aware palette recommendation system grounded in empirical data responsive to user constraints. Our findings highlight the importance of selecting categorical palettes aligned with specific analytical tasks and demonstrate how task-aware modeling enables more reliable palette design. CatPAL translates empirical results into a practical tool that supports user-specified colors or shapes and returns ranked palette recommendations adaptable to a range of tasks.
For Practitioners
Visualization designers, data scientists, dashboard developers, data journalists, and charting-tool builders who choose categorical palettes for multiclass data will find this paper useful. Practitioners can use CatPAL, our public web-based tool, to generate ranked color, shape, or redundant palettes tailored to their category count and analysis task while pinning preferred brand colors. Our findings also offer direct guidance: palettes should match the viewer's analytic goal rather than rely on one-size-fits-all defaults, and redundant color+shape encoding helps at high category counts but can hurt at low ones. Tool builders can integrate our openly released perceptual rankings and models into their own systems.