Directed Diversity: Leveraging Language Embedding Distances for Collective Creativity in Crowd Ideation
This addresses the challenge of enhancing creativity in crowdsourcing for applications like health promotion, though it is incremental as it builds on prior methods for reducing redundancy.
The paper tackled the problem of redundant ideas in crowd ideation by introducing Directed Diversity, an automatic prompt selection method that uses language model embedding distances to maximize diversity, and showed in simulation and user studies that it improves collective creativity across various diversity metrics for crowdsourcing motivational messages.
Crowdsourcing can collect many diverse ideas by prompting ideators individually, but this can generate redundant ideas. Prior methods reduce redundancy by presenting peers' ideas or peer-proposed prompts, but these require much human coordination. We introduce Directed Diversity, an automatic prompt selection approach that leverages language model embedding distances to maximize diversity. Ideators can be directed towards diverse prompts and away from prior ideas, thus improving their collective creativity. Since there are diverse metrics of diversity, we present a Diversity Prompting Evaluation Framework consolidating metrics from several research disciplines to analyze along the ideation chain - prompt selection, prompt creativity, prompt-ideation mediation, and ideation creativity. Using this framework, we evaluated Directed Diversity in a series of a simulation study and four user studies for the use case of crowdsourcing motivational messages to encourage physical activity. We show that automated diverse prompting can variously improve collective creativity across many nuanced metrics of diversity.