cs.HCNov 10, 2026
SaveCUVE: Making Supervised Classification more Accessible through Visualization
Organizations: Department of Computer Science, University of Victoria, Victoria, Canada
Abstract
We present CUVE, an interface that enables people to build classifiers by generating visualizations that are interpretable by both humans and learning algorithms (the Visualization as Intermediate Representation approach). This UI enables users to create supervised classifiers and to visually investigate how to improve them and how they carry out their function. A preliminary study investigates the usability of our prototype and compares it with a traditional text-based programming interface.
Figures & tables
Figure 1: File Uploading and Inspection screen.
Figure 2: Tab 3: Creating visualizations.
Figure 3: Algorithm training and tests.
Figure 4: Algorithm training and tests.
Figure 5: An example of the Visualization that the instructor guided the participate to create during the study, using water probability datasets.
Figure 6: Average differences in aggregated SUS scores. Error bars represent 95% bootstrapped CI.