Forecasting high-impact research topics via machine learning on evolving knowledge graphs
arXiv:2402.08640 · doi:10.1088/2632-2153/add6ef
Abstract
The exponential growth in scientific publications poses a severe challenge for human researchers. It forces attention to more narrow sub-fields, which makes it challenging to discover new impactful research ideas and collaborations outside one's own field. While there are ways to predict a scientific paper's future citation counts, they need the research to be finished and the paper written, usually assessing impact long after the idea was 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. It 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 (AUC values beyond 0.9 for most experiments), 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.
15 pages, 12 figures, Comments welcome!
References in corpus (15)
- Machine learning and the physical sciences
- Exceptional Topology of Non-Hermitian Systems
- The physics of higher-order interactions in complex systems
- Quantifying Long-Term Scientific Impact
- Gemini: A Family of Highly Capable Multimodal Models
- Defining and identifying Sleeping Beauties in science
- On scientific understanding with artificial intelligence
- Constraints on cosmic strings using data from the first Advanced LIGO observing run
- Artificial Intelligence and Machine Learning for Quantum Technologies
- Predicting the long-term citation impact of recent publications
- Predicting Research Trends with Semantic and Neural Networks with an application in Quantum Physics
- BGnet: Accurate and rapid background estimation in single-molecule localization microscopy with deep neural nets
- Predicting the Future of AI with AI: High-quality link prediction in an exponentially growing knowledge network
- Learning phase transitions from dynamics
- Detecting signal from science:The structure of research communities and prior knowledge improves prediction of genetic regulatory experiments