File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Constructing public health evidence knowledge graph for decision-making support from COVID-19 literature of modelling study

TitleConstructing public health evidence knowledge graph for decision-making support from COVID-19 literature of modelling study
Authors
KeywordsCOVID-19
Decision-making support
Evidence-based public health
Knowledge graph
Issue Date2021
Citation
Journal of Safety Science and Resilience, 2021, v. 2, n. 3, p. 146-156 How to Cite?
AbstractThe needs of mitigating COVID-19 epidemic prompt policymakers to make public health-related decision under the guidelines of science. Tremendous unstructured COVID-19 publications make it challenging for policymakers to obtain relevant evidence. Knowledge graphs (KGs) can formalize unstructured knowledge into structured form and have been used in supporting decision-making recently. Here, we introduce a novel framework that can extract the COVID-19 public health evidence knowledge graph (CPHE-KG) from papers relating to a modelling study. We screen out a corpus of 3096 COVID-19 modelling study papers by performing a literature assessment process. We define a novel annotation schema to construct the COVID-19 modelling study-related IE dataset (CPHIE). We also propose a novel multi-tasks document-level information extraction model SS-DYGIE++ based on the dataset. Leveraging the model on the new corpus, we construct CPHE-KG containing 60,967 entities and 51,140 relations. Finally, we seek to apply our KG to support evidence querying and evidence mapping visualization. Our SS-DYGIE++(SpanBERT) model has achieved a F1 score of 0.77 and 0.55 respectively in document-level entity recognition and coreference resolution tasks. It has also shown high performance in the relation identification task. With evidence querying, our KG can present the dynamic transmissions of COVID-19 pandemic in different countries and regions. The evidence mapping of our KG can show the impacts of variable non-pharmacological interventions to COVID-19 pandemic. Analysis demonstrates the quality of our KG and shows that it has the potential to support COVID-19 policy making in public health.
Persistent Identifierhttp://hdl.handle.net/10722/330780
ISSN
2023 Impact Factor: 3.7
2023 SCImago Journal Rankings: 0.895
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorYang, Yunrong-
dc.contributor.authorCao, Zhidong-
dc.contributor.authorZhao, Pengfei-
dc.contributor.authorZeng, Dajun Daniel-
dc.contributor.authorZhang, Qingpeng-
dc.contributor.authorLuo, Yin-
dc.date.accessioned2023-09-05T12:14:13Z-
dc.date.available2023-09-05T12:14:13Z-
dc.date.issued2021-
dc.identifier.citationJournal of Safety Science and Resilience, 2021, v. 2, n. 3, p. 146-156-
dc.identifier.issn2096-7527-
dc.identifier.urihttp://hdl.handle.net/10722/330780-
dc.description.abstractThe needs of mitigating COVID-19 epidemic prompt policymakers to make public health-related decision under the guidelines of science. Tremendous unstructured COVID-19 publications make it challenging for policymakers to obtain relevant evidence. Knowledge graphs (KGs) can formalize unstructured knowledge into structured form and have been used in supporting decision-making recently. Here, we introduce a novel framework that can extract the COVID-19 public health evidence knowledge graph (CPHE-KG) from papers relating to a modelling study. We screen out a corpus of 3096 COVID-19 modelling study papers by performing a literature assessment process. We define a novel annotation schema to construct the COVID-19 modelling study-related IE dataset (CPHIE). We also propose a novel multi-tasks document-level information extraction model SS-DYGIE++ based on the dataset. Leveraging the model on the new corpus, we construct CPHE-KG containing 60,967 entities and 51,140 relations. Finally, we seek to apply our KG to support evidence querying and evidence mapping visualization. Our SS-DYGIE++(SpanBERT) model has achieved a F1 score of 0.77 and 0.55 respectively in document-level entity recognition and coreference resolution tasks. It has also shown high performance in the relation identification task. With evidence querying, our KG can present the dynamic transmissions of COVID-19 pandemic in different countries and regions. The evidence mapping of our KG can show the impacts of variable non-pharmacological interventions to COVID-19 pandemic. Analysis demonstrates the quality of our KG and shows that it has the potential to support COVID-19 policy making in public health.-
dc.languageeng-
dc.relation.ispartofJournal of Safety Science and Resilience-
dc.subjectCOVID-19-
dc.subjectDecision-making support-
dc.subjectEvidence-based public health-
dc.subjectKnowledge graph-
dc.titleConstructing public health evidence knowledge graph for decision-making support from COVID-19 literature of modelling study-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.jnlssr.2021.08.002-
dc.identifier.scopuseid_2-s2.0-85126971280-
dc.identifier.volume2-
dc.identifier.issue3-
dc.identifier.spage146-
dc.identifier.epage156-
dc.identifier.eissn2666-4496-
dc.identifier.isiWOS:001059249600001-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats