Machine learning prediction of academic collaboration networks
Abstract We investigate the different roles played by nodes’ network and non-network attributes in explaining the formation of European university collaborations from 2011 to 2016, in three European Research Council (ERC) domains: Social Sciences and Humanities (SSH), Physical and Engineering Scienc...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2022-12-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-022-26531-1 |
_version_ | 1797977489862033408 |
---|---|
author | Giuliano Resce Antonio Zinilli Giovanni Cerulli |
author_facet | Giuliano Resce Antonio Zinilli Giovanni Cerulli |
author_sort | Giuliano Resce |
collection | DOAJ |
description | Abstract We investigate the different roles played by nodes’ network and non-network attributes in explaining the formation of European university collaborations from 2011 to 2016, in three European Research Council (ERC) domains: Social Sciences and Humanities (SSH), Physical and Engineering Sciences (PE), Life Sciences (LS), as well as multidisciplinary collaborations. On link formation in collaboration networks, existing research has not yet compared and simultaneously examined both network and non-network attributes. Using four machine learning predictive algorithms (LASSO, Neural Network, Gradient Boosting, and Random Forest) our results show that, over various model specifications: (i) best model link formation accuracy is larger than 80%, (ii) among the non-network attributes, public funding plays an important role in PE and LS, (iii) network attributes count more than non-network attributes for the formation, sensibly increasing accuracy, (iv) feature-importance scores show a different ordering in the four domains, thus signalling different modes of knowledge production and transmission taking place within these different scientific communities. |
first_indexed | 2024-04-11T05:07:44Z |
format | Article |
id | doaj.art-a428eada2ddb453f9a77be5b4b7c809a |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-04-11T05:07:44Z |
publishDate | 2022-12-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-a428eada2ddb453f9a77be5b4b7c809a2022-12-25T12:15:18ZengNature PortfolioScientific Reports2045-23222022-12-0112111610.1038/s41598-022-26531-1Machine learning prediction of academic collaboration networksGiuliano Resce0Antonio Zinilli1Giovanni Cerulli2Department of Economics, University of MoliseResearch Institute on Sustainable Economic Growth, National Research Council of ItalyResearch Institute on Sustainable Economic Growth, National Research Council of ItalyAbstract We investigate the different roles played by nodes’ network and non-network attributes in explaining the formation of European university collaborations from 2011 to 2016, in three European Research Council (ERC) domains: Social Sciences and Humanities (SSH), Physical and Engineering Sciences (PE), Life Sciences (LS), as well as multidisciplinary collaborations. On link formation in collaboration networks, existing research has not yet compared and simultaneously examined both network and non-network attributes. Using four machine learning predictive algorithms (LASSO, Neural Network, Gradient Boosting, and Random Forest) our results show that, over various model specifications: (i) best model link formation accuracy is larger than 80%, (ii) among the non-network attributes, public funding plays an important role in PE and LS, (iii) network attributes count more than non-network attributes for the formation, sensibly increasing accuracy, (iv) feature-importance scores show a different ordering in the four domains, thus signalling different modes of knowledge production and transmission taking place within these different scientific communities.https://doi.org/10.1038/s41598-022-26531-1 |
spellingShingle | Giuliano Resce Antonio Zinilli Giovanni Cerulli Machine learning prediction of academic collaboration networks Scientific Reports |
title | Machine learning prediction of academic collaboration networks |
title_full | Machine learning prediction of academic collaboration networks |
title_fullStr | Machine learning prediction of academic collaboration networks |
title_full_unstemmed | Machine learning prediction of academic collaboration networks |
title_short | Machine learning prediction of academic collaboration networks |
title_sort | machine learning prediction of academic collaboration networks |
url | https://doi.org/10.1038/s41598-022-26531-1 |
work_keys_str_mv | AT giulianoresce machinelearningpredictionofacademiccollaborationnetworks AT antoniozinilli machinelearningpredictionofacademiccollaborationnetworks AT giovannicerulli machinelearningpredictionofacademiccollaborationnetworks |