Research hypothesis generation over scientific knowledge graphs

Generating research hypotheses is a crucial step in scientific investigation that involves the creation of precise, verifiable, and logically valid statements that can be empirically examined. Therefore, many efforts have been made to automate or assist this process through the use of various Artifi...

ver descrição completa

Detalhes bibliográficos
Autores: Borrego Díaz, Agustín, Dessì, Danilo, Ayala Hernández, Daniel, Hernández Salmerón, Inmaculada Concepción, Osborne, Francesco, Recupero, Diego Reforgiato, Buscaldi, Davide, Ruiz Cortés, David, Motta, Enrico
Formato: artículo
Estado:Versión publicada
Fecha de publicación:2025
País:España
Recursos:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/181544
Acesso em linha:https://hdl.handle.net/11441/181544
https://doi.org/10.1016/j.knosys.2025.113280
Access Level:acceso abierto
Palavra-chave:Hypothesis generation
Knowledge graphs
Link prediction
Scholarly domain
Scientific facts
Artificial Intelligence
id ES_042fc2eefb4ca2bbe6ef72104ca026a8
oai_identifier_str oai:idus.us.es:11441/181544
network_acronym_str ES
network_name_str España
repository_id_str
spelling Research hypothesis generation over scientific knowledge graphsBorrego Díaz, AgustínDessì, DaniloAyala Hernández, DanielHernández Salmerón, Inmaculada ConcepciónOsborne, FrancescoRecupero, Diego ReforgiatoBuscaldi, DavideRuiz Cortés, DavidMotta, EnricoHypothesis generationKnowledge graphsLink predictionScholarly domainScientific factsArtificial IntelligenceGenerating research hypotheses is a crucial step in scientific investigation that involves the creation of precise, verifiable, and logically valid statements that can be empirically examined. Therefore, many efforts have been made to automate or assist this process through the use of various Artificial Intelligence solutions. However, most existing methods are tailored to very specific domains, particularly within the biomedical field. There have been recent attempts to formalize hypothesis generation as a link prediction task over knowledge graphs. This solution is potentially domain-independent and applicable across diverse disciplines. Nevertheless, current approaches for link prediction, which typically rely on embedding models or path-based methods, have shown limited success in accurately predicting new hypotheses. To address these limitations, this paper introduces ResearchLink, an innovative and domain-independent methodology for hypothesis generation over knowledge graphs. ResearchLink combines path-based features and knowledge graph embeddings with text embeddings, capturing the semantic context of entities within a given corpus, and integrates additional information from bibliometric databases to improve research collaboration predictions. To conduct a rigorous evaluation of ResearchLink, we constructed CSKG-600, a new dataset for hypothesis generation, consisting of 600 statements that were manually labeled by domain experts. ResearchLink achieved outstanding performance (78.7% P@20), significantly outperforming alternative approaches such as TransH (71.8%), TransD (71.7%), and RotatE (70.7%).ElsevierLenguajes y Sistemas InformáticosMinistry of University and Research (MUR)2025info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttps://hdl.handle.net/11441/181544https://doi.org/10.1016/j.knosys.2025.113280reponame:idUS. Depósito de Investigación de la Universidad de Sevillainstname:Universidad de Sevilla (US)InglésKnowledge-Based Systems, 315 (113280), 1 p.-12 p..https://www.sciencedirect.com/science/article/pii/S0950705125003272?via%3Dihubinfo:eu-repo/semantics/openAccessoai:idus.us.es:11441/1815442026-06-17T12:51:07Z
dc.title.none.fl_str_mv Research hypothesis generation over scientific knowledge graphs
title Research hypothesis generation over scientific knowledge graphs
spellingShingle Research hypothesis generation over scientific knowledge graphs
Borrego Díaz, Agustín
Hypothesis generation
Knowledge graphs
Link prediction
Scholarly domain
Scientific facts
Artificial Intelligence
title_short Research hypothesis generation over scientific knowledge graphs
title_full Research hypothesis generation over scientific knowledge graphs
title_fullStr Research hypothesis generation over scientific knowledge graphs
title_full_unstemmed Research hypothesis generation over scientific knowledge graphs
title_sort Research hypothesis generation over scientific knowledge graphs
dc.creator.none.fl_str_mv Borrego Díaz, Agustín
Dessì, Danilo
Ayala Hernández, Daniel
Hernández Salmerón, Inmaculada Concepción
Osborne, Francesco
Recupero, Diego Reforgiato
Buscaldi, Davide
Ruiz Cortés, David
Motta, Enrico
author Borrego Díaz, Agustín
author_facet Borrego Díaz, Agustín
Dessì, Danilo
Ayala Hernández, Daniel
Hernández Salmerón, Inmaculada Concepción
Osborne, Francesco
Recupero, Diego Reforgiato
Buscaldi, Davide
Ruiz Cortés, David
Motta, Enrico
author_role author
author2 Dessì, Danilo
Ayala Hernández, Daniel
Hernández Salmerón, Inmaculada Concepción
Osborne, Francesco
Recupero, Diego Reforgiato
Buscaldi, Davide
Ruiz Cortés, David
Motta, Enrico
author2_role author
author
author
author
author
author
author
author
dc.contributor.none.fl_str_mv Lenguajes y Sistemas Informáticos
Ministry of University and Research (MUR)
dc.subject.none.fl_str_mv Hypothesis generation
Knowledge graphs
Link prediction
Scholarly domain
Scientific facts
Artificial Intelligence
topic Hypothesis generation
Knowledge graphs
Link prediction
Scholarly domain
Scientific facts
Artificial Intelligence
description Generating research hypotheses is a crucial step in scientific investigation that involves the creation of precise, verifiable, and logically valid statements that can be empirically examined. Therefore, many efforts have been made to automate or assist this process through the use of various Artificial Intelligence solutions. However, most existing methods are tailored to very specific domains, particularly within the biomedical field. There have been recent attempts to formalize hypothesis generation as a link prediction task over knowledge graphs. This solution is potentially domain-independent and applicable across diverse disciplines. Nevertheless, current approaches for link prediction, which typically rely on embedding models or path-based methods, have shown limited success in accurately predicting new hypotheses. To address these limitations, this paper introduces ResearchLink, an innovative and domain-independent methodology for hypothesis generation over knowledge graphs. ResearchLink combines path-based features and knowledge graph embeddings with text embeddings, capturing the semantic context of entities within a given corpus, and integrates additional information from bibliometric databases to improve research collaboration predictions. To conduct a rigorous evaluation of ResearchLink, we constructed CSKG-600, a new dataset for hypothesis generation, consisting of 600 statements that were manually labeled by domain experts. ResearchLink achieved outstanding performance (78.7% P@20), significantly outperforming alternative approaches such as TransH (71.8%), TransD (71.7%), and RotatE (70.7%).
publishDate 2025
dc.date.none.fl_str_mv 2025
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/11441/181544
https://doi.org/10.1016/j.knosys.2025.113280
url https://hdl.handle.net/11441/181544
https://doi.org/10.1016/j.knosys.2025.113280
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Knowledge-Based Systems, 315 (113280), 1 p.-12 p..
https://www.sciencedirect.com/science/article/pii/S0950705125003272?via%3Dihub
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:idUS. Depósito de Investigación de la Universidad de Sevilla
instname:Universidad de Sevilla (US)
instname_str Universidad de Sevilla (US)
reponame_str idUS. Depósito de Investigación de la Universidad de Sevilla
collection idUS. Depósito de Investigación de la Universidad de Sevilla
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869402776538185728
score 15,81155

Registos relacionados