Impact4Cast: Forecasting high-impact research topics via machine learning on evolving knowledge graphs

The exponential growth in scientific publications poses a severe challenge for human researchers, forcing them to focus on narrower sub-fields and making it difficult to discover new, impactful research ideas and collaborations outside their own fields. Although there are methods to predict a scientific paper's future citation counts, these require the research to be completed and the paper to be written, often assessing impact long after the idea was first conceived. Here we show how to predict the impact of onsets of ideas that have never been published by researchers. For that, we developed a large evolving knowledge graph built from more than 21 million scientific papers, which combines a semantic network created from the content of the papers and an impact network created from the historic citations of papers. Using machine learning, we can predict the dynamic of the evolving network into the future with high accuracy, and thereby the impact of new research directions. We envision that the ability to predict the impact of new ideas will be a crucial component of future artificial muses that can inspire new impactful and interesting scientific ideas.