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...
Saved in:
| Main Authors: | , |
|---|---|
| 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 |