Previously, we improved creativity by automatically directing the crowd with diverse prompts Directed Diversity (Cox et al., CHI’21). Here, we further improve creativity by providing real-time feedback on the ideations.
We propose Interpretable Directed Diversity to automatically score the quality and diversity of written ideations and use explainable AI techniques to generate Attribution, Contrastive Attribution, and Counterfactual Suggestion explanations to provide feedback for improvement. Through a formative user study and summative user studies, we characterized how users leveraged the explanations to be more creative, and showed that multiple explanations improves the diversity of ideations.
Congratulations to team members Yunlong Wang and undergraduate intern Priyadarshini Venkatesh!
Yunlong Wang, Priyadarshini Venkatesh, and Brian Y. Lim. 2022. Interpretable Directed Diversity: Leveraging Model Explanations for Iterative Crowd Ideation. In Proceedings of the international Conference on Human Factors in Computing Systems. CHI ’22.