VizCrit: Exploring Strategies for Displaying Computational Feedback in a Visual Design Tool

TL;DR

VizCrit, a system for providing computational feedback that supports the actionability spectrum, is introduced through algorithmic issue detection and visual annotation generation, and the implications for AI in Creativity Support Tools are discussed.

Abstract

Visual design instructors often provide multi-modal feedback, mixing annotations with text. Prior theory emphasizes the importance of actionable feedback, where "actionability" lies on a spectrum--from surfacing relevant design concepts to suggesting concrete fixes. How might creativity tools implement annotations that support such feedback, and how does the actionability of feedback impact novices' process-related behaviors, perceptions of creativity, learning of design principles, and overall outcomes? We introduce VizCrit, a system for providing computational feedback that supports the actionability spectrum, realized through algorithmic issue detection and visual annotation generation. In a between-subjects study (N=36), novices revised a design under one of three conditions: textbook-based, awareness-centered, or solution-centered feedback. We found that solution-centered feedback led to fewer design issues and higher self-perceived creativity compared with textbook-based feedback, although expert ratings on creativity showed no significant differences. We discuss the implications for AI in Creativity Support Tools, including the potential of calibrating feedback actionability to help novices balance productivity with learning, growth, and developing design awareness.

Figures (3)

• Figure 7: Distribution of participants' ($n=36$, 12 per feedback condition) self-ratings on their final design, creative ownership, confidence, design knowledge, and overall experience with design annotations (awareness-centered or solution-centered). There were no statistically significant differences in these ratings. However, the ratings on whether the design felt like "my own work" seem to contradict our hypotheses about creative ownership. While we expected solution-centered participants to have the least ownership, they felt it equally as much if not more compared with other feedback conditions.
• Figure 8: Example participant designs and expert ratings across conditions. Experts annotated design issues and parameter changes, and provided ratings of creativity (1: low, 10: high) and degree of change relative to the seed design.
• Figure 9: Iterative design of the whitespace design probes: our set of 4 annotations at the left for whitespace (2 awareness-centered top, 2 solution-centered bottom), along with the expert iterations of each. Most started with their preferred of our two designs and made revisions from there.