{"id":"https://openalex.org/W1997754546","doi":"https://doi.org/10.1045/november14-tkaczyk","title":"GROTOAP2 The Methodology of Creating a Large Ground Truth Dataset of Scientific Articles","display_name":"GROTOAP2 The Methodology of Creating a Large Ground Truth Dataset of Scientific Articles","publication_year":2014,"publication_date":"2014-11-01","ids":{"openalex":"https://openalex.org/W1997754546","doi":"https://doi.org/10.1045/november14-tkaczyk","mag":"1997754546"},"language":"en","primary_location":{"id":"doi:10.1045/november14-tkaczyk","is_oa":true,"landing_page_url":"https://doi.org/10.1045/november14-tkaczyk","pdf_url":null,"source":{"id":"https://openalex.org/S119508283","display_name":"D-Lib Magazine","issn_l":"1082-9873","issn":["1082-9873"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310316316","host_organization_name":"Corporation for National Research Initiatives","host_organization_lineage":["https://openalex.org/P4310316316"],"host_organization_lineage_names":["Corporation for National Research Initiatives"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"D-Lib Magazine","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1045/november14-tkaczyk","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061634863","display_name":"Dominika Tkaczyk","orcid":"https://orcid.org/0000-0001-5055-7876"},"institutions":[{"id":"https://openalex.org/I4654613","display_name":"University of Warsaw","ror":"https://ror.org/039bjqg32","country_code":"PL","type":"education","lineage":["https://openalex.org/I4654613"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Dominika Tkaczyk","raw_affiliation_strings":["Centre for Open Science, Interdisciplinary Centre for Mathematical and Computational Modelling, University of Warsaw, Poland"],"affiliations":[{"raw_affiliation_string":"Centre for Open Science, Interdisciplinary Centre for Mathematical and Computational Modelling, University of Warsaw, Poland","institution_ids":["https://openalex.org/I4654613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071222040","display_name":"Pawe\u0142 Szostek","orcid":null},"institutions":[{"id":"https://openalex.org/I4654613","display_name":"University of Warsaw","ror":"https://ror.org/039bjqg32","country_code":"PL","type":"education","lineage":["https://openalex.org/I4654613"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Pawel Szostek","raw_affiliation_strings":["Centre for Open Science, Interdisciplinary Centre for Mathematical and Computational Modelling, University of Warsaw, Poland"],"affiliations":[{"raw_affiliation_string":"Centre for Open Science, Interdisciplinary Centre for Mathematical and Computational Modelling, University of Warsaw, Poland","institution_ids":["https://openalex.org/I4654613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010356596","display_name":"\u0141ukasz Bolikowski","orcid":"https://orcid.org/0000-0003-1048-6051"},"institutions":[{"id":"https://openalex.org/I4654613","display_name":"University of Warsaw","ror":"https://ror.org/039bjqg32","country_code":"PL","type":"education","lineage":["https://openalex.org/I4654613"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"\u0141ukasz Bolikowski","raw_affiliation_strings":["Centre for Open Science, Interdisciplinary Centre for Mathematical and Computational Modelling, University of Warsaw, Poland"],"affiliations":[{"raw_affiliation_string":"Centre for Open Science, Interdisciplinary Centre for Mathematical and Computational Modelling, University of Warsaw, Poland","institution_ids":["https://openalex.org/I4654613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061634863"],"corresponding_institution_ids":["https://openalex.org/I4654613"],"apc_list":null,"apc_paid":null,"fwci":0.5686,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.66211435,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"20","issue":"11/12","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9376999735832214,"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":0.9376999735832214,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9083999991416931,"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/T10028","display_name":"Topic Modeling","score":0.9067000150680542,"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/ground-truth","display_name":"Ground truth","score":0.7541211843490601},{"id":"https://openalex.org/keywords/common-ground","display_name":"Common ground","score":0.4956270456314087},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.355332612991333},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.35320398211479187},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23782595992088318},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.20655936002731323},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07906439900398254}],"concepts":[{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.7541211843490601},{"id":"https://openalex.org/C2777877512","wikidata":"https://www.wikidata.org/wiki/Q1116097","display_name":"Common ground","level":2,"score":0.4956270456314087},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.355332612991333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.35320398211479187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23782595992088318},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.20655936002731323},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07906439900398254}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1045/november14-tkaczyk","is_oa":true,"landing_page_url":"https://doi.org/10.1045/november14-tkaczyk","pdf_url":null,"source":{"id":"https://openalex.org/S119508283","display_name":"D-Lib Magazine","issn_l":"1082-9873","issn":["1082-9873"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310316316","host_organization_name":"Corporation for National Research Initiatives","host_organization_lineage":["https://openalex.org/P4310316316"],"host_organization_lineage_names":["Corporation for National Research Initiatives"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"D-Lib Magazine","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1045/november14-tkaczyk","is_oa":true,"landing_page_url":"https://doi.org/10.1045/november14-tkaczyk","pdf_url":null,"source":{"id":"https://openalex.org/S119508283","display_name":"D-Lib Magazine","issn_l":"1082-9873","issn":["1082-9873"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310316316","host_organization_name":"Corporation for National Research Initiatives","host_organization_lineage":["https://openalex.org/P4310316316"],"host_organization_lineage_names":["Corporation for National Research Initiatives"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"D-Lib Magazine","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4307535225","https://openalex.org/W82897008","https://openalex.org/W2905544777","https://openalex.org/W3097373745","https://openalex.org/W125944254","https://openalex.org/W2220635983","https://openalex.org/W169904705","https://openalex.org/W3208234354","https://openalex.org/W2131052232","https://openalex.org/W2971867419"],"abstract_inverted_index":{"Scientific":[0],"literature":[1],"analysis":[2],"improves":[3],"knowledge":[4],"propagation":[5],"and":[6,13,26,72,86,118,138,171,195,200],"plays":[7],"a":[8,77,99],"key":[9],"role":[10],"in":[11,18,44,112],"understanding":[12,49],"assessment":[14],"of":[15,32,39,52,55,90,102,109,120,188],"scholarly":[16],"communication":[17],"scientific":[19,33,110,141],"world.":[20],"In":[21,92],"recent":[22],"years":[23],"many":[24],"tools":[25],"services":[27],"for":[28,65,116,129,135,175],"analysing":[29],"the":[30,40,50,56,87,186,191,197],"content":[31,122,139,187],"articles":[34,111,148],"have":[35],"been":[36],"developed.":[37],"One":[38],"most":[41],"important":[42],"tasks":[43],"this":[45,93],"research":[46],"area":[47],"is":[48,59,145,156,169],"roles":[51],"different":[53],"parts":[54],"document.":[57],"It":[58],"impossible":[60],"to":[61,68,166],"build":[62],"effective":[63],"solutions":[64],"problems":[66],"related":[67],"document":[69,121],"fragments":[70,108],"classification":[71],"evaluate":[73],"their":[74],"performance":[75],"without":[76],"reliable":[78],"test":[79],"set,":[80],"that":[81],"contains":[82],"both":[83],"input":[84],"documents":[85],"expected":[88],"results":[89],"classification.":[91],"paper":[94],"we":[95],"present":[96],"GROTOAP2":[97,125,155,168],"\ufffd":[98,132],"large":[100,177],"dataset":[101,144],"ground":[103],"truth":[104],"files":[105],"containing":[106],"labelled":[107],"PDF":[113],"format,":[114],"useful":[115],"training":[117,130],"evaluation":[119,198],"analysis-related":[123],"solutions.":[124],"was":[126],"successfully":[127],"used":[128,165],"CERMINE":[131],"our":[133],"system":[134],"extracting":[136],"metadata":[137],"from":[140,149,179],"articles.":[142],"The":[143,162,183],"based":[146],"on":[147],"PubMed":[150],"Central":[151],"Open":[152,159],"Access":[153,160],"Subset.":[154],"published":[157],"under":[158],"license.":[161],"semi-automatic":[163],"method":[164],"construct":[167],"scalable":[170],"can":[172],"be":[173],"adjusted":[174],"building":[176],"datasets":[178],"other":[180],"data":[181],"sources.":[182],"article":[184],"presents":[185],"GROTOAP2,":[189],"describes":[190],"entire":[192],"creation":[193],"process":[194],"reports":[196],"methodology":[199],"results.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}