Interpretable Directed Diversity: Leveraging Model Explanations for Iterative Crowd Ideation

TL;DR

This paper introduces Interpretable Directed Diversity, an AI-driven method that automatically predicts ideation quality and diversity, providing multi-faceted explanations to help crowdworkers iteratively improve their creative ideas.

Contribution

It presents a novel AI approach that offers explainable feedback for crowd ideation, reducing reliance on human facilitators and enhancing creativity support tools.

Findings

Explanations helped users focus and improve ideation diversity.

Users found explanation feedback useful for guiding improvements.

Diversity increased with explanation-based feedback compared to no feedback.

Abstract

Feedback in creativity support tools can help crowdworkers to improve their ideations. However, current feedback methods require human assessment from facilitators or peers. This is not scalable to large crowds. We propose Interpretable Directed Diversity to automatically predict ideation quality and diversity scores, and provide AI explanations - Attribution, Contrastive Attribution, and Counterfactual Suggestions - to feedback on why ideations were scored (low), and how to get higher scores. These explanations provide multi-faceted feedback as users iteratively improve their ideations. We conducted formative and controlled user studies to understand the usage and usefulness of explanations to improve ideation diversity and quality. Users appreciated that explanation feedback helped focus their efforts and provided directions for improvement. This resulted in explanations improving diversity compared to no feedback or feedback with scores only. Hence, our approach opens opportunities for explainable AI towards scalable and rich feedback for iterative crowd ideation and creativity support tools.