In this project, we explore how digital platforms can support patient-led research by enabling collective intelligence to emerge through better connection and coordination of participants with complementary expertise. We designed and tested a recommender system on the JOGL platform that suggests contributors to open project needs based on skill similarity, project activity, and topical interest.
Through a combination of targeted email notifications, platform engagement analysis, and qualitative case studies, we show that engagement is not only driven by skill match but also by project visibility, popularity, and activity. Two contrasting case studies—Quantified Flu (which succeeded in developing a prototype) and CoughCheck (which stalled due to a mismatch in skills)—highlight the critical role of effective matchmaking.
This work advances our understanding of how “architectures of attention” can be designed to support open, distributed research efforts, particularly those initiated by patient communities. The tools and findings from this study—supported by NESTA—are relevant for broader applications in open science and citizen innovation.
📄 Full methodology, analysis, and insights are detailed in the final report, available here: hal-04167308.
Funded by NESTA’s Collective Intelligence Grants Programme
Interaction Data Lab 