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

TL;DR

This paper introduces VizCrit, a system that provides computational feedback supporting various levels of actionability in visual design, and studies its impact on novice designers' behaviors and perceptions.

Contribution

It presents VizCrit, a novel system that generates actionable visual annotations for design feedback, and evaluates its effects on novice design revision processes.

Findings

Solution-centered feedback reduces design issues and boosts perceived creativity.

Expert ratings show no significant difference in creativity across feedback types.

Calibrating feedback actionability can balance productivity and learning in design.

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.