Directed Diversity: Leveraging Language Embedding Distances for Collective Creativity in Crowd Ideation

TL;DR

This paper introduces Directed Diversity, an automatic prompt selection method using language embedding distances to enhance diversity and collective creativity in crowd ideation, reducing redundancy without human coordination.

Contribution

It presents a novel embedding-based prompt selection approach and a comprehensive diversity evaluation framework for crowd ideation tasks.

Findings

Automated diverse prompting improves collective creativity across multiple metrics.

Directed Diversity effectively reduces idea redundancy in crowdsourcing.

The framework enables nuanced analysis of diversity throughout the ideation process.

Abstract

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.