{"id":"https://openalex.org/W2786693834","doi":"https://doi.org/10.1371/journal.pcbi.1005962","title":"A comprehensive and quantitative comparison of text-mining in 15 million full-text articles versus their corresponding abstracts","display_name":"A comprehensive and quantitative comparison of text-mining in 15 million full-text articles versus their corresponding abstracts","publication_year":2018,"publication_date":"2018-02-15","ids":{"openalex":"https://openalex.org/W2786693834","doi":"https://doi.org/10.1371/journal.pcbi.1005962","mag":"2786693834","pmid":"https://pubmed.ncbi.nlm.nih.gov/29447159"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1005962","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1005962","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1005962&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1005962&type=printable","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014841854","display_name":"David Westergaard","orcid":"https://orcid.org/0000-0003-0128-8432"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]},{"id":"https://openalex.org/I2801134892","display_name":"Novo Nordisk Foundation","ror":"https://ror.org/04txyc737","country_code":"DK","type":"facility","lineage":["https://openalex.org/I2801134892"]},{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"David Westergaard","raw_affiliation_strings":["Center for Biological Sequence Analysis, Department of Bio and Health Informatics, Technical University of Denmark, Lyngby, Denmark","Novo Nordisk Foundation Center for Protein Research, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Biological Sequence Analysis, Department of Bio and Health Informatics, Technical University of Denmark, Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]},{"raw_affiliation_string":"Novo Nordisk Foundation Center for Protein Research, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I2801134892","https://openalex.org/I124055696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113657498","display_name":"Hans-Henrik St\u00e6rfeldt","orcid":null},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Hans-Henrik St\u00e6rfeldt","raw_affiliation_strings":["Center for Biological Sequence Analysis, Department of Bio and Health Informatics, Technical University of Denmark, Lyngby, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Biological Sequence Analysis, Department of Bio and Health Informatics, Technical University of Denmark, Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036135871","display_name":"Christian T\u00f8nsberg","orcid":"https://orcid.org/0000-0001-9504-2163"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Christian T\u00f8nsberg","raw_affiliation_strings":["Office for Innovation and Sector Services, Technical Information Center of Denmark, Technical University of Denmark, Lyngby, Denmark"],"raw_orcid":"https://orcid.org/0000-0001-9504-2163","affiliations":[{"raw_affiliation_string":"Office for Innovation and Sector Services, Technical Information Center of Denmark, Technical University of Denmark, Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005772961","display_name":"Lars Juhl Jensen","orcid":"https://orcid.org/0000-0001-7885-715X"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]},{"id":"https://openalex.org/I2801134892","display_name":"Novo Nordisk Foundation","ror":"https://ror.org/04txyc737","country_code":"DK","type":"facility","lineage":["https://openalex.org/I2801134892"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Lars Juhl Jensen","raw_affiliation_strings":["Novo Nordisk Foundation Center for Protein Research, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark"],"raw_orcid":"https://orcid.org/0000-0001-7885-715X","affiliations":[{"raw_affiliation_string":"Novo Nordisk Foundation Center for Protein Research, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I2801134892","https://openalex.org/I124055696"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011862057","display_name":"S\u00f8ren Brunak","orcid":"https://orcid.org/0000-0003-0316-5866"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"S\u00f8ren Brunak","raw_affiliation_strings":["Center for Biological Sequence Analysis, Department of Bio and Health Informatics, Technical University of Denmark, Lyngby, Denmark"],"raw_orcid":"https://orcid.org/0000-0003-0316-5866","affiliations":[{"raw_affiliation_string":"Center for Biological Sequence Analysis, Department of Bio and Health Informatics, Technical University of Denmark, Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5005772961","https://openalex.org/A5011862057"],"corresponding_institution_ids":["https://openalex.org/I124055696","https://openalex.org/I2801134892","https://openalex.org/I96673099"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2655,"currency":"USD","value_usd":2655},"fwci":8.7227,"has_fulltext":true,"cited_by_count":172,"citation_normalized_percentile":{"value":0.98526094,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"14","issue":"2","first_page":"e1005962","last_page":"e1005962"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9843000173568726,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5106349587440491},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.4423033595085144},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4235602617263794},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3676704168319702},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.35975727438926697},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.3384475111961365},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3380086421966553},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.20905417203903198}],"concepts":[{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5106349587440491},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.4423033595085144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4235602617263794},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3676704168319702},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35975727438926697},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.3384475111961365},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3380086421966553},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.20905417203903198}],"mesh":[{"descriptor_ui":"D000043","descriptor_name":"Abstracting and Indexing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000043","descriptor_name":"Abstracting and Indexing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000043","descriptor_name":"Abstracting and Indexing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005189","descriptor_name":"False Positive Reactions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005189","descriptor_name":"False Positive Reactions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005189","descriptor_name":"False Positive Reactions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005796","descriptor_name":"Genes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005796","descriptor_name":"Genes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005796","descriptor_name":"Genes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010506","descriptor_name":"Periodicals as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010506","descriptor_name":"Periodicals as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010506","descriptor_name":"Periodicals as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012372","descriptor_name":"ROC Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012372","descriptor_name":"ROC Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012372","descriptor_name":"ROC Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019540","descriptor_name":"Area Under Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019540","descriptor_name":"Area Under Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019540","descriptor_name":"Area Under Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":8,"locations":[{"id":"doi:10.1371/journal.pcbi.1005962","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1005962","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1005962&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},{"id":"pmid:29447159","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29447159","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLoS computational biology","raw_type":null},{"id":"pmh:oai:pure.atira.dk:publications/1d40ef32-b0fb-48c8-989c-3ba2f1a5cee6","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/1d40ef32-b0fb-48c8-989c-3ba2f1a5cee6","pdf_url":"https://curis.ku.dk/ws/files/210007970/journal.pcbi.1005962.pdf","source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Westergaard , D , St\u00e6rfeldt , H-H , T\u00f8nsberg , C , Jensen , L J & Brunak , S 2018 , ' A comprehensive and quantitative comparison of text-mining in 15 million full-text articles versus their corresponding abstracts ' , PLoS Computational Biology , vol. 14 , no. 2 , e1005962 . https://doi.org/10.1371/journal.pcbi.1005962","raw_type":"article"},{"id":"pmh:oai:doaj.org/article:4aedde1c9d994b6bacc3882e0b9a9e00","is_oa":true,"landing_page_url":"https://doaj.org/article/4aedde1c9d994b6bacc3882e0b9a9e00","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Computational Biology, Vol 14, Iss 2, p e1005962 (2018)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:4757972","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5831415","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:figshare.com:article/5892088","is_oa":true,"landing_page_url":"https://figshare.com/articles/dataset/A_comprehensive_and_quantitative_comparison_of_text-mining_in_15_million_full-text_articles_versus_their_corresponding_abstracts/5892088","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dataset"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/1d40ef32-b0fb-48c8-989c-3ba2f1a5cee6","is_oa":true,"landing_page_url":"https://curis.ku.dk/portal/da/publications/a-comprehensive-and-quantitative-comparison-of-textmining-in-15-million-fulltext-articles-versus-their-corresponding-abstracts(1d40ef32-b0fb-48c8-989c-3ba2f1a5cee6).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.atira.dk:publications/ce5dc6fb-8603-4ae4-8266-ebf8452d0a22","is_oa":true,"landing_page_url":"https://orbit.dtu.dk/en/publications/ce5dc6fb-8603-4ae4-8266-ebf8452d0a22","pdf_url":null,"source":{"id":"https://openalex.org/S4306400705","display_name":"Technical University of Denmark, DTU Orbit (Technical University of Denmark, DTU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I96673099","host_organization_name":"Technical University of Denmark","host_organization_lineage":["https://openalex.org/I96673099"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Westergaard , D , St\u00e6rfeldt , H H , T\u00f8nsberg , C , Jensen , L J &amp; Brunak , S 2018 , ' A comprehensive and quantitative comparison of text-mining in 15 million full-text articles versus their corresponding abstracts ' , P L o S Computational Biology (Online) , vol. 14 , no. 2 , e1005962 . https://doi.org/10.1371/journal.pcbi.1005962","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.1005962","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1005962","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1005962&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6000000238418579}],"awards":[{"id":"https://openalex.org/G4282887365","display_name":null,"funder_award_id":"NNF14CC0001","funder_id":"https://openalex.org/F4320322436","funder_display_name":"Novo Nordisk"},{"id":"https://openalex.org/G6662978750","display_name":null,"funder_award_id":"NNF14CC0001","funder_id":"https://openalex.org/F4320325957","funder_display_name":"Novo Nordisk Fonden"}],"funders":[{"id":"https://openalex.org/F4320322436","display_name":"Novo Nordisk","ror":"https://ror.org/0435rc536"},{"id":"https://openalex.org/F4320322975","display_name":"Danish e-Infrastructure Cooperation","ror":"https://ror.org/03ge1nb22"},{"id":"https://openalex.org/F4320325957","display_name":"Novo Nordisk Fonden","ror":"https://ror.org/04txyc737"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2786693834.pdf","grobid_xml":"https://content.openalex.org/works/W2786693834.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W253402974","https://openalex.org/W845836637","https://openalex.org/W1479703980","https://openalex.org/W1700570096","https://openalex.org/W1968761064","https://openalex.org/W1994306321","https://openalex.org/W2004910511","https://openalex.org/W2005958938","https://openalex.org/W2010798628","https://openalex.org/W2025971693","https://openalex.org/W2031618431","https://openalex.org/W2033237963","https://openalex.org/W2033853342","https://openalex.org/W2053039860","https://openalex.org/W2053673723","https://openalex.org/W2058190388","https://openalex.org/W2061598441","https://openalex.org/W2064354603","https://openalex.org/W2069172670","https://openalex.org/W2071972943","https://openalex.org/W2075322787","https://openalex.org/W2076230195","https://openalex.org/W2096173332","https://openalex.org/W2097498916","https://openalex.org/W2098679902","https://openalex.org/W2103017472","https://openalex.org/W2104093114","https://openalex.org/W2104655105","https://openalex.org/W2105440823","https://openalex.org/W2105924489","https://openalex.org/W2110256992","https://openalex.org/W2115746733","https://openalex.org/W2121570534","https://openalex.org/W2122904379","https://openalex.org/W2124617249","https://openalex.org/W2126469373","https://openalex.org/W2127603354","https://openalex.org/W2128386749","https://openalex.org/W2138838049","https://openalex.org/W2142937131","https://openalex.org/W2159092541","https://openalex.org/W2159482845","https://openalex.org/W2166633748","https://openalex.org/W2168909179","https://openalex.org/W2212494754","https://openalex.org/W2230587849","https://openalex.org/W2294516783","https://openalex.org/W2356560879","https://openalex.org/W2471579714","https://openalex.org/W2481381417","https://openalex.org/W2548932017","https://openalex.org/W2559588208","https://openalex.org/W2728845751","https://openalex.org/W2739999456","https://openalex.org/W2888211956","https://openalex.org/W4294216483","https://openalex.org/W6674567323"],"related_works":["https://openalex.org/W4391026046","https://openalex.org/W1147368348","https://openalex.org/W3030538550","https://openalex.org/W2160121913","https://openalex.org/W2736149021","https://openalex.org/W4297803820","https://openalex.org/W3148490189","https://openalex.org/W4299638067","https://openalex.org/W1562480646","https://openalex.org/W2050178430"],"abstract_inverted_index":{"Across":[0],"academia":[1],"and":[2,65,85,95,123],"industry,":[3],"text":[4,78,126],"mining":[5,23,79,127],"has":[6,28],"become":[7],"a":[8,90],"popular":[9],"strategy":[10],"for":[11],"keeping":[12],"up":[13],"with":[14],"the":[15,19,25,55,60,75,110],"rapid":[16],"growth":[17],"of":[18,24,35,46,77,128],"scientific":[20,26,50],"literature.":[21],"Text":[22],"literature":[27],"mostly":[29],"been":[30],"carried":[31],"out":[32],"on":[33,98,116],"collections":[34],"abstracts,":[36],"due":[37],"to":[38,112],"their":[39,99],"availability.":[40],"Here":[41],"we":[42],"present":[43],"an":[44],"analysis":[45],"15":[47],"million":[48,118],"English":[49],"full-text":[51,129],"articles":[52,130],"published":[53,82],"during":[54,68],"period":[56],"1823-2016.":[57],"We":[58,73,107],"describe":[59],"development":[61],"in":[62,121],"article":[63],"length":[64],"publication":[66],"sub-topics":[67],"these":[69],"nearly":[70],"250":[71],"years.":[72],"showcase":[74],"potential":[76],"by":[80],"extracting":[81],"protein-protein,":[83],"disease-gene,":[84],"protein":[86],"subcellular":[87],"associations":[88],"using":[89,101,133],"named":[91],"entity":[92],"recognition":[93],"system,":[94],"quantitatively":[96],"report":[97],"accuracy":[100],"gold":[102],"standard":[103],"benchmark":[104],"data":[105],"sets.":[106],"subsequently":[108],"compare":[109],"findings":[111],"corresponding":[113],"results":[114],"obtained":[115],"16.5":[117],"abstracts":[119,134],"included":[120],"MEDLINE":[122],"show":[124],"that":[125],"consistently":[131],"outperforms":[132],"only.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":28},{"year":2019,"cited_by_count":26},{"year":2018,"cited_by_count":15}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
