{"id":"https://openalex.org/W2889191490","doi":"https://doi.org/10.1002/pra2.2017.14505401005","title":"Big data, big metadata and quantitative study of science: A workflow model for big scientometrics","display_name":"Big data, big metadata and quantitative study of science: A workflow model for big scientometrics","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2889191490","doi":"https://doi.org/10.1002/pra2.2017.14505401005","mag":"2889191490"},"language":"en","primary_location":{"id":"doi:10.1002/pra2.2017.14505401005","is_oa":false,"landing_page_url":"https://doi.org/10.1002/pra2.2017.14505401005","pdf_url":null,"source":{"id":"https://openalex.org/S4393918545","display_name":"Proceedings of the Association for Information Science and Technology","issn_l":"2373-9231","issn":["2373-9231"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Association for Information Science and Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022757536","display_name":"Sarah Bratt","orcid":"https://orcid.org/0000-0002-3642-4425"},"institutions":[{"id":"https://openalex.org/I70983195","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02","country_code":"US","type":"education","lineage":["https://openalex.org/I70983195"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sarah Bratt","raw_affiliation_strings":["Syracuse University  USA","Syracuse University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Syracuse University  USA","institution_ids":["https://openalex.org/I70983195"]},{"raw_affiliation_string":"Syracuse University, USA","institution_ids":["https://openalex.org/I70983195"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058044503","display_name":"Jeff Hemsley","orcid":"https://orcid.org/0000-0001-9276-6983"},"institutions":[{"id":"https://openalex.org/I70983195","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02","country_code":"US","type":"education","lineage":["https://openalex.org/I70983195"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jeff Hemsley","raw_affiliation_strings":["Syracuse University  USA","Syracuse University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Syracuse University  USA","institution_ids":["https://openalex.org/I70983195"]},{"raw_affiliation_string":"Syracuse University, USA","institution_ids":["https://openalex.org/I70983195"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041928722","display_name":"Jian Qin","orcid":"https://orcid.org/0000-0002-7094-2867"},"institutions":[{"id":"https://openalex.org/I70983195","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02","country_code":"US","type":"education","lineage":["https://openalex.org/I70983195"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jian Qin","raw_affiliation_strings":["School of Information Studies Syracuse University  USA","School of Information Studies, Syracuse University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Studies Syracuse University  USA","institution_ids":["https://openalex.org/I70983195"]},{"raw_affiliation_string":"School of Information Studies, Syracuse University, USA","institution_ids":["https://openalex.org/I70983195"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038173240","display_name":"Mark R. Costa","orcid":"https://orcid.org/0000-0001-7967-980X"},"institutions":[{"id":"https://openalex.org/I70983195","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02","country_code":"US","type":"education","lineage":["https://openalex.org/I70983195"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mark Costa","raw_affiliation_strings":["Newhouse School of Public Communications Syracuse University  USA","Newhouse School of Public Communications, Syracuse University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Newhouse School of Public Communications Syracuse University  USA","institution_ids":["https://openalex.org/I70983195"]},{"raw_affiliation_string":"Newhouse School of Public Communications, Syracuse University, USA","institution_ids":["https://openalex.org/I70983195"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5022757536","https://openalex.org/A5038173240","https://openalex.org/A5041928722","https://openalex.org/A5058044503"],"corresponding_institution_ids":["https://openalex.org/I70983195"],"apc_list":null,"apc_paid":null,"fwci":2.0865,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.92266203,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"54","issue":"1","first_page":"36","last_page":"45"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9997000098228455,"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/T11937","display_name":"Research Data Management Practices","score":0.9987999796867371,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9560999870300293,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/metadata","display_name":"Metadata","score":0.8297055959701538},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7923964858055115},{"id":"https://openalex.org/keywords/cyberinfrastructure","display_name":"Cyberinfrastructure","score":0.7409377098083496},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7171416878700256},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7023221254348755},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6544691324234009},{"id":"https://openalex.org/keywords/scientometrics","display_name":"Scientometrics","score":0.6124477386474609},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.496098130941391},{"id":"https://openalex.org/keywords/metadata-modeling","display_name":"Metadata modeling","score":0.43629151582717896},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.42800483107566833},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3030354380607605},{"id":"https://openalex.org/keywords/data-element","display_name":"Data element","score":0.1719273030757904},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.16615653038024902},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.11741253733634949}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8297055959701538},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7923964858055115},{"id":"https://openalex.org/C2776397876","wikidata":"https://www.wikidata.org/wiki/Q1450531","display_name":"Cyberinfrastructure","level":2,"score":0.7409377098083496},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7171416878700256},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7023221254348755},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6544691324234009},{"id":"https://openalex.org/C525823164","wikidata":"https://www.wikidata.org/wiki/Q472342","display_name":"Scientometrics","level":2,"score":0.6124477386474609},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.496098130941391},{"id":"https://openalex.org/C110326360","wikidata":"https://www.wikidata.org/wiki/Q17149476","display_name":"Metadata modeling","level":4,"score":0.43629151582717896},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.42800483107566833},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3030354380607605},{"id":"https://openalex.org/C30872290","wikidata":"https://www.wikidata.org/wiki/Q1172389","display_name":"Data element","level":3,"score":0.1719273030757904},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.16615653038024902},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.11741253733634949},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1002/pra2.2017.14505401005","is_oa":false,"landing_page_url":"https://doi.org/10.1002/pra2.2017.14505401005","pdf_url":null,"source":{"id":"https://openalex.org/S4393918545","display_name":"Proceedings of the Association for Information Science and Technology","issn_l":"2373-9231","issn":["2373-9231"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Association for Information Science and Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332162","display_name":"Centers for Disease Control and Prevention","ror":"https://ror.org/042twtr12"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1932742904","https://openalex.org/W1998599063","https://openalex.org/W2006153666","https://openalex.org/W2013818045","https://openalex.org/W2050974180","https://openalex.org/W2058995344","https://openalex.org/W2149085946","https://openalex.org/W2154513453","https://openalex.org/W2166784953","https://openalex.org/W2319794630","https://openalex.org/W2330103991","https://openalex.org/W2476760196","https://openalex.org/W2620485168","https://openalex.org/W4246954632","https://openalex.org/W4254607142"],"related_works":["https://openalex.org/W2003742646","https://openalex.org/W4224036053","https://openalex.org/W2366936177","https://openalex.org/W3122624872","https://openalex.org/W1773645839","https://openalex.org/W2380261968","https://openalex.org/W3084772717","https://openalex.org/W2796209520","https://openalex.org/W2907247951","https://openalex.org/W2136226335"],"abstract_inverted_index":{"ABSTRACT":[0],"Large":[1],"cyberinfrastructure\u2010enabled":[2],"data":[3,12,25,46],"repositories":[4,47],"generate":[5],"massive":[6],"amounts":[7],"of":[8,19,31,38,44,61,116,134,139,147],"metadata,":[9],"enabling":[10],"big":[11,39,53,70,110,148],"analytics":[13,55,65],"to":[14,57,95,131],"leverage":[15],"on":[16],"the":[17,28,42,50,58,102,117,132,137,144],"intersection":[18],"technological":[20],"and":[21,48,66,80,93,104,136,141,156],"methodological":[22,73,89,121],"advances":[23],"in":[24,41,52,68,124],"science":[26,138,140],"for":[27,64],"quantitative":[29],"study":[30],"science.":[32],"This":[33],"paper":[34,99,126],"introduces":[35],"a":[36,108,128],"definition":[37],"metadata":[40,54,111,149],"context":[43],"scientific":[45],"discusses":[49],"challenges":[51],"due":[56],"messiness,":[59],"lack":[60],"structures":[62],"suitable":[63],"heterogeneity":[67],"such":[69],"metadata.":[71],"A":[72],"framework":[74,90,122],"is":[75,127,150],"proposed,":[76],"which":[77],"contains":[78],"conceptual":[79],"computational":[81],"workflows":[82],"intercepting":[83],"through":[84],"collaborative":[85],"documentation.":[86],"The":[87,98,120],"workflow\u2010based":[88,118],"promotes":[91],"transparency":[92],"contributes":[94],"research":[96,155],"reproducibility.":[97],"also":[100],"describes":[101],"experience":[103],"lessons":[105],"learned":[106],"from":[107,154],"four\u2010year":[109],"project":[112],"involving":[113],"all":[114],"aspects":[115],"methodologies.":[119],"presented":[123],"this":[125],"timely":[129],"contribution":[130],"field":[133],"scientometrics":[135],"policy":[142,157],"as":[143],"potential":[145],"value":[146],"drawing":[151],"more":[152],"attention":[153],"maker":[158],"communities.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}