{"id":"https://openalex.org/W3097085767","doi":"https://doi.org/10.5334/dsj-2020-042","title":"ODDPub \u2013 a Text-Mining Algorithm to Detect Data Sharing in Biomedical Publications","display_name":"ODDPub \u2013 a Text-Mining Algorithm to Detect Data Sharing in Biomedical Publications","publication_year":2020,"publication_date":"2020-10-29","ids":{"openalex":"https://openalex.org/W3097085767","doi":"https://doi.org/10.5334/dsj-2020-042","mag":"3097085767"},"language":"en","primary_location":{"id":"doi:10.5334/dsj-2020-042","is_oa":true,"landing_page_url":"https://doi.org/10.5334/dsj-2020-042","pdf_url":"http://datascience.codata.org/articles/10.5334/dsj-2020-042/galley/1008/download/","source":{"id":"https://openalex.org/S62969111","display_name":"Data Science Journal","issn_l":"1683-1470","issn":["1683-1470"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320511","host_organization_name":"Ubiquity Press","host_organization_lineage":["https://openalex.org/P4310320511"],"host_organization_lineage_names":["Ubiquity Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Science Journal","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://datascience.codata.org/articles/10.5334/dsj-2020-042/galley/1008/download/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070578048","display_name":"Nico Riedel","orcid":"https://orcid.org/0000-0002-3808-1163"},"institutions":[{"id":"https://openalex.org/I4210139777","display_name":"Berlin Institute of Health at Charit\u00e9 - Universit\u00e4tsmedizin Berlin","ror":"https://ror.org/0493xsw21","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210139777","https://openalex.org/I7877124"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Nico Riedel","raw_affiliation_strings":["QUEST Center for Transforming Biomedical Research, Berlin Institute of Health (BIH), Berlin"],"affiliations":[{"raw_affiliation_string":"QUEST Center for Transforming Biomedical Research, Berlin Institute of Health (BIH), Berlin","institution_ids":["https://openalex.org/I4210139777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017415827","display_name":"Miriam Kip","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139777","display_name":"Berlin Institute of Health at Charit\u00e9 - Universit\u00e4tsmedizin Berlin","ror":"https://ror.org/0493xsw21","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210139777","https://openalex.org/I7877124"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Miriam Kip","raw_affiliation_strings":["QUEST Center for Transforming Biomedical Research, Berlin Institute of Health (BIH), Berlin"],"affiliations":[{"raw_affiliation_string":"QUEST Center for Transforming Biomedical Research, Berlin Institute of Health (BIH), Berlin","institution_ids":["https://openalex.org/I4210139777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081113127","display_name":"Evgeny Bobrov","orcid":"https://orcid.org/0000-0002-2368-464X"},"institutions":[{"id":"https://openalex.org/I4210139777","display_name":"Berlin Institute of Health at Charit\u00e9 - Universit\u00e4tsmedizin Berlin","ror":"https://ror.org/0493xsw21","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210139777","https://openalex.org/I7877124"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Evgeny Bobrov","raw_affiliation_strings":["QUEST Center for Transforming Biomedical Research, Berlin Institute of Health (BIH), Berlin"],"affiliations":[{"raw_affiliation_string":"QUEST Center for Transforming Biomedical Research, Berlin Institute of Health (BIH), Berlin","institution_ids":["https://openalex.org/I4210139777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5070578048"],"corresponding_institution_ids":["https://openalex.org/I4210139777"],"apc_list":{"value":350,"currency":"GBP","value_usd":429},"apc_paid":{"value":350,"currency":"GBP","value_usd":429},"fwci":6.1198,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.96627343,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"19","issue":"1","first_page":"42","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8037738800048828},{"id":"https://openalex.org/keywords/open-data","display_name":"Open data","score":0.6105790734291077},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5455195903778076},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4771411120891571},{"id":"https://openalex.org/keywords/data-sharing","display_name":"Data sharing","score":0.46712902188301086},{"id":"https://openalex.org/keywords/transparency","display_name":"Transparency (behavior)","score":0.46563687920570374},{"id":"https://openalex.org/keywords/open-science","display_name":"Open science","score":0.4379788935184479},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.42976799607276917},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4188898205757141},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2975754141807556},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.1288059949874878},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08554300665855408}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8037738800048828},{"id":"https://openalex.org/C2780535194","wikidata":"https://www.wikidata.org/wiki/Q309901","display_name":"Open data","level":2,"score":0.6105790734291077},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5455195903778076},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4771411120891571},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.46712902188301086},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.46563687920570374},{"id":"https://openalex.org/C2778149293","wikidata":"https://www.wikidata.org/wiki/Q309823","display_name":"Open science","level":2,"score":0.4379788935184479},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.42976799607276917},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4188898205757141},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2975754141807556},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.1288059949874878},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08554300665855408},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.5334/dsj-2020-042","is_oa":true,"landing_page_url":"https://doi.org/10.5334/dsj-2020-042","pdf_url":"http://datascience.codata.org/articles/10.5334/dsj-2020-042/galley/1008/download/","source":{"id":"https://openalex.org/S62969111","display_name":"Data Science Journal","issn_l":"1683-1470","issn":["1683-1470"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320511","host_organization_name":"Ubiquity Press","host_organization_lineage":["https://openalex.org/P4310320511"],"host_organization_lineage_names":["Ubiquity Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Science Journal","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a48231ea85ce445da610b09ca1800065","is_oa":true,"landing_page_url":"https://doaj.org/article/a48231ea85ce445da610b09ca1800065","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data Science Journal, Vol 19, Iss 1 (2020)","raw_type":"article"},{"id":"pmh:oai:ojs.datascience.codata.org:article/1216","is_oa":true,"landing_page_url":"https://datascience.codata.org/jms/article/view/dsj-2020-042","pdf_url":null,"source":{"id":"https://openalex.org/S62969111","display_name":"Data Science Journal","issn_l":"1683-1470","issn":["1683-1470"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320511","host_organization_name":"Ubiquity Press","host_organization_lineage":["https://openalex.org/P4310320511"],"host_organization_lineage_names":["Ubiquity Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data Science Journal; Vol 19 (2020); 42","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.5334/dsj-2020-042","is_oa":true,"landing_page_url":"https://doi.org/10.5334/dsj-2020-042","pdf_url":"http://datascience.codata.org/articles/10.5334/dsj-2020-042/galley/1008/download/","source":{"id":"https://openalex.org/S62969111","display_name":"Data Science Journal","issn_l":"1683-1470","issn":["1683-1470"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320511","host_organization_name":"Ubiquity Press","host_organization_lineage":["https://openalex.org/P4310320511"],"host_organization_lineage_names":["Ubiquity Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Science Journal","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3097085767.pdf","grobid_xml":"https://content.openalex.org/works/W3097085767.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2031934506","https://openalex.org/W2037620269","https://openalex.org/W2045657963","https://openalex.org/W2047659102","https://openalex.org/W2047864778","https://openalex.org/W2235540394","https://openalex.org/W2302501749","https://openalex.org/W2566090830","https://openalex.org/W2773787581","https://openalex.org/W2790735892","https://openalex.org/W2795141263","https://openalex.org/W2799486656","https://openalex.org/W2883630435","https://openalex.org/W2923030710","https://openalex.org/W2951111744","https://openalex.org/W2955244474","https://openalex.org/W3005930964","https://openalex.org/W4391861343","https://openalex.org/W4394553094","https://openalex.org/W6687794633"],"related_works":["https://openalex.org/W2400751427","https://openalex.org/W2105854671","https://openalex.org/W2482697570","https://openalex.org/W2738396072","https://openalex.org/W4362646606","https://openalex.org/W2345835657","https://openalex.org/W3134224924","https://openalex.org/W4285196440","https://openalex.org/W4229077818","https://openalex.org/W3097500482"],"abstract_inverted_index":{"Open":[0,28,45,70,144,156,167,214,223,241],"research":[1,75,81],"data":[2,106],"are":[3],"increasingly":[4],"recognized":[5],"as":[6,252],"a":[7,59,78,97,148,179,245],"quality":[8],"indicator":[9],"and":[10,18,40,66,86,152,183,200],"an":[11,48,253],"important":[12],"resource":[13],"to":[14,36,191,221],"increase":[15],"transparency,":[16],"robustness":[17],"collaboration":[19],"in":[20,30,47,57,196,244],"science.":[21],"However,":[22],"no":[23],"standardized":[24],"way":[25],"of":[26,44,69,99,150,154,165,176,181,185,202,211,230],"reporting":[27],"Data":[29,46,55,145,157,224,242],"publications":[31,65,76,132,146,177,212,243],"exists,":[32],"making":[33],"it":[34,117],"difficult":[35],"find":[37],"shared":[38,120],"datasets":[39,194],"assess":[41,222],"the":[42,114,192,197,228],"prevalence":[43],"automated":[49],"fashion.":[50],"We":[51,187],"developed":[52,96],"ODDPub":[53,103,249],"(Open":[54,123],"Detection":[56],"Publications),":[58],"text-mining":[60],"algorithm":[61,142,205],"that":[62],"screens":[63],"biomedical":[64,80],"detects":[67],"cases":[68],"Data.":[71,215],"Using":[72],"English-language":[73],"original":[74],"from":[77,89,135],"single":[79],"institution":[82],"(<em>n</em>":[83,91,162,173],"=":[84,92,163,174],"8689)":[85],"randomly":[87,133],"selected":[88,134],"PubMed":[90,199],"1500)":[93],"we":[94,128],"iteratively":[95],"set":[98],"derived":[100],"keyword":[101],"categories.":[102],"can":[104,118,206,217,237],"detect":[105,119],"sharing":[107,225],"through":[108],"field-specific":[109],"repositories,":[110],"general-purpose":[111],"repositories":[112],"or":[113,234],"supplement.":[115],"Additionally,":[116],"analysis":[121],"code":[122],"Code).":[124],"To":[125],"validate":[126],"ODDPub,":[127],"manually":[129],"screened":[130],"792":[131],"PubMed.":[136],"On":[137],"this":[138],"validation":[139],"dataset,":[140],"our":[141,189],"detected":[143,159,170],"with":[147,178],"sensitivity":[149,180],"0.73":[151,182],"specificity":[153,184],"0.97.":[155],"was":[158,169],"for":[160,171,213],"11.5%":[161],"91)":[164],"publications.":[166],"Code":[168],"1.4%":[172],"11)":[175],"1.00.":[186],"compared":[188],"results":[190],"linked":[193],"found":[195],"databases":[198],"Web":[201],"Science.":[203],"Our":[204],"automatically":[207],"screen":[208],"large":[209],"numbers":[210],"It":[216,236],"thus":[218],"be":[219],"used":[220],"rates":[226],"on":[227,256],"level":[229],"subject":[231],"areas,":[232],"journals,":[233],"institutions.":[235],"also":[238],"identify":[239],"individual":[240],"larger":[246],"publication":[247],"corpus.":[248],"is":[250],"published":[251],"R":[254],"package":[255],"GitHub.":[257]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
