The wicked problem of plastic pollution is one of the key global challenges. Finding adequate solutions to this complex problem requires cross-cultural and inter-organizational collaboration among diverse sets of stakeholders. In this context, the Ellen Mac Arthur Foundation approaches the problem of plastic pollution not only by involving experts into innovation processes but also by integrating the general public in form of an IT enabled crowdsourcing initiative. In this study, we analyze the outcomes of these actions with the help of automated text mining techniques. Our analysis demonstrates significant differences between the solutions given by experts and the crowd along various criteria. Further, this study provides guidance for practitioners on how to integrate diverse sets of individuals in problem solving processes with the help of information systems technologies. Especially for sustainability issues affecting both, developed and developing regions.

Effective exploration of a landscape full of crowdsourced ideas depends on the right search strategy, as well as the level of granularity in the representation. To categorize similar ideas on different granularity levels modern natural language processing methods and clustering algorithms can be usefully applied. However, the value of machine-based categorizations is dependent on their comprehensibility and coherence with human similarity perceptions. We find that machine-based and human similarity allocations are more likely to converge when comparing ideas across more distant solution clusters than within closely related ones. Our exploratory study contributes to research on the navigability of idea landscapes, by pointing out the impact of granularity on the exploration of crowdsourced knowledge. For practitioners, we provide insights on how to organize the search for the best possible solutions and control the cognitive demand of searchers.