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. 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 scientifi...

Full description

Saved in:
Bibliographic Details
Main Authors: Xuemei Gu, Mario Krenn
Format: Article
Language:English
Published: IOP Publishing 2025-01-01
Series:Machine Learning: Science and Technology
Subjects:
Online Access:https://doi.org/10.1088/2632-2153/add6ef
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849730574951907328
author Xuemei Gu
Mario Krenn
author_facet Xuemei Gu
Mario Krenn
author_sort Xuemei Gu
collection DOAJ
description 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.
format Article
id doaj-art-73c0e10b5e7e4f1fbdb06ec74ae9a825
institution DOAJ
issn 2632-2153
language English
publishDate 2025-01-01
publisher IOP Publishing
record_format Article
series Machine Learning: Science and Technology
spelling doaj-art-73c0e10b5e7e4f1fbdb06ec74ae9a8252025-08-20T03:08:50ZengIOP PublishingMachine Learning: Science and Technology2632-21532025-01-016202504110.1088/2632-2153/add6efForecasting high-impact research topics via machine learning on evolving knowledge graphsXuemei Gu0https://orcid.org/0000-0002-0734-432XMario Krenn1https://orcid.org/0000-0003-1620-9207Max Planck Institute for the Science of Light , Staudtstrasse 2, 91058 Erlangen, GermanyMax Planck Institute for the Science of Light , Staudtstrasse 2, 91058 Erlangen, GermanyThe 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.https://doi.org/10.1088/2632-2153/add6efimpact predictionknowledge graphmachine learningcomputational science
spellingShingle Xuemei Gu
Mario Krenn
Forecasting high-impact research topics via machine learning on evolving knowledge graphs
Machine Learning: Science and Technology
impact prediction
knowledge graph
machine learning
computational science
title Forecasting high-impact research topics via machine learning on evolving knowledge graphs
title_full Forecasting high-impact research topics via machine learning on evolving knowledge graphs
title_fullStr Forecasting high-impact research topics via machine learning on evolving knowledge graphs
title_full_unstemmed Forecasting high-impact research topics via machine learning on evolving knowledge graphs
title_short Forecasting high-impact research topics via machine learning on evolving knowledge graphs
title_sort forecasting high impact research topics via machine learning on evolving knowledge graphs
topic impact prediction
knowledge graph
machine learning
computational science
url https://doi.org/10.1088/2632-2153/add6ef
work_keys_str_mv AT xuemeigu forecastinghighimpactresearchtopicsviamachinelearningonevolvingknowledgegraphs
AT mariokrenn forecastinghighimpactresearchtopicsviamachinelearningonevolvingknowledgegraphs