Abstract
The prediction of exceptional or surprising growth in research is an issue with deep roots and few practical solutions. In this study, we develop and validate a novel approach to forecasting growth in highly specific research communities. Each research community is represented by a cluster of papers. Multiple indicators were tested, and a composite indicator was created that predicts which research communities will experience exceptional growth over the next three years. The accuracy of this predictor was tested using hundreds of thousands of community-level forecasts and was found to exceed the performance benchmarks established in Intelligence Advanced Research Projects Activity's (IARPA) Foresight Using Scientific Exposition (FUSE) program in six of nine major fields in science. Furthermore, 10 of 11 disciplines within the Computing Technologies field met the benchmarks. Specific detailed forecast examples are given and evaluated, and a critical evaluation of the forecasting approach is also provided.
Highlights
The prediction of exceptional or surprising growth in research is of keen interest to policy makers in government, military, and commercial organizations [1]
The prediction of exceptional growth in research followed a case study approach. Prior research, such as the National Science Foundation’s Technology in Retrospect and Critical Events in Science (TRACES) program in the 1960s, Defense Advanced Research Projects Agency’s Topic Detection and Tracking (TDT) program in the 1990s, and Intelligence Advanced Research Projects Activity (IARPA)’s Foresight Using Scientific Exposition (FUSE) program from the early 2010s focused on dozens of areas of research that were relevant to the policy maker
The clustering approach used in this study is to identify Kuhnian research communities (RC) using the “linkages among citations” that was recommended by Kuhn [14] but that was not scaled up to cluster millions of documents until 2012 with the introduction of the VOS (Visualization of Similarities) clustering methodology by researchers at the Centre for Science and Technology Studies (CWTS) at Leiden University [15]
Summary
The prediction of exceptional or surprising growth in research is of keen interest to policy makers in government, military, and commercial organizations [1]. We calculate CSI using forecasts of exceptional growth (compared to outcomes) of clusters of documents, or research communities (RC), from our comprehensive, highly granular models of science.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
