Catching but a glimpse?—Navigating crowdsourced solution spaces with transformer-based language models

Abstract

Current approaches for identifying valuable content among the multitude of solutions in crowdsourcing contests are resource-intensive and constrained by human processing capacity. As idea convergence processes usually focus on filtering out single ideas, the potential of solution-related knowledge among the heterogeneous ideas is not exploited in a sustainable manner. Transformer-based language models can process large sets of idea descriptions into digestible structures, with unprecedented capabilities for understanding and manipulating text. This study explores how they can help organizations and decision-makers navigate crowdsourced solution spaces efficiently and comprehensively. Inspired by theoretical concepts around problem-solving and innovation search, we conceptualize three related search practices—direct search, cluster exploration and pattern discovery—and illustrate them on 289 crowdsourced ideas for future mobility and energy services. Direct search can assist in identifying solutions that match pressing needs or subproblems. Cluster exploration enables aggregating semantically similar ideas into clusters to identify relevant needs. Pattern discovery synthesizes themes and interrelations to build a holistic understanding of potential solutions. The study contributes to the application of AI-assisted idea convergence by adding a new perspective beyond filtering out a few promising ideas.