{"id":"https://openalex.org/W3024646987","doi":"https://doi.org/10.1162/qss_a_00049","title":"Using supervised learning to classify metadata of research data by field of study","display_name":"Using supervised learning to classify metadata of research data by field of study","publication_year":2020,"publication_date":"2020-05-04","ids":{"openalex":"https://openalex.org/W3024646987","doi":"https://doi.org/10.1162/qss_a_00049","mag":"3024646987"},"language":"en","primary_location":{"id":"doi:10.1162/qss_a_00049","is_oa":true,"landing_page_url":"https://doi.org/10.1162/qss_a_00049","pdf_url":"https://direct.mit.edu/qss/article-pdf/1/2/525/1885831/qss_a_00049.pdf","source":{"id":"https://openalex.org/S4210195326","display_name":"Quantitative Science Studies","issn_l":"2641-3337","issn":["2641-3337"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT 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":"Quantitative Science Studies","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://direct.mit.edu/qss/article-pdf/1/2/525/1885831/qss_a_00049.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005159253","display_name":"Tobias Weber","orcid":"https://orcid.org/0000-0003-1815-7041"},"institutions":[{"id":"https://openalex.org/I4210163716","display_name":"Leibniz Supercomputing Centre","ror":"https://ror.org/05558nw16","country_code":"DE","type":"facility","lineage":["https://openalex.org/I109144446","https://openalex.org/I4210163716"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Tobias Weber","raw_affiliation_strings":["Munich Network Management Team, Leibniz Supercomputing Centre (Germany)"],"raw_orcid":"https://orcid.org/0000-0003-1815-7041","affiliations":[{"raw_affiliation_string":"Munich Network Management Team, Leibniz Supercomputing Centre (Germany)","institution_ids":["https://openalex.org/I4210163716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055672826","display_name":"Dieter Kranzlm\u00fcller","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dieter Kranzlm\u00fcller","raw_affiliation_strings":["Munich Network Management Team, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen (Germany)"],"raw_orcid":"https://orcid.org/0000-0002-8319-0123","affiliations":[{"raw_affiliation_string":"Munich Network Management Team, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen (Germany)","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032664719","display_name":"Michael Fromm","orcid":"https://orcid.org/0000-0002-7244-4191"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Fromm","raw_affiliation_strings":["Database Systems Group, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen (Germany)"],"raw_orcid":"https://orcid.org/0000-0002-7244-4191","affiliations":[{"raw_affiliation_string":"Database Systems Group, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen (Germany)","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080554091","display_name":"Nelson Tavares de Sousa","orcid":"https://orcid.org/0000-0003-1866-7156"},"institutions":[{"id":"https://openalex.org/I32021983","display_name":"Christian-Albrechts-Universit\u00e4t zu Kiel","ror":"https://ror.org/04v76ef78","country_code":"DE","type":"education","lineage":["https://openalex.org/I32021983"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nelson Tavares de Sousa","raw_affiliation_strings":["Software Engineering Group, Kiel University (Germany)"],"raw_orcid":"https://orcid.org/0000-0003-1866-7156","affiliations":[{"raw_affiliation_string":"Software Engineering Group, Kiel University (Germany)","institution_ids":["https://openalex.org/I32021983"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005159253"],"corresponding_institution_ids":["https://openalex.org/I4210163716"],"apc_list":{"value":800,"currency":"USD","value_usd":800},"apc_paid":{"value":800,"currency":"USD","value_usd":800},"fwci":0.6795,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.76206762,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9815999865531921,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9815999865531921,"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":0.9765999913215637,"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/T11937","display_name":"Research Data Management Practices","score":0.9625999927520752,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.8612772226333618},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7574372291564941},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.6972625851631165},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.5625672936439514},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5509874820709229},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.5385794043540955},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4768748879432678},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4445219039916992},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4416593611240387},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4320884346961975},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.41738349199295044},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41065680980682373},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37324783205986023},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1943407654762268},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10402980446815491},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08285510540008545}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8612772226333618},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7574372291564941},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.6972625851631165},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.5625672936439514},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5509874820709229},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5385794043540955},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4768748879432678},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4445219039916992},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4416593611240387},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4320884346961975},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.41738349199295044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41065680980682373},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37324783205986023},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1943407654762268},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10402980446815491},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08285510540008545},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/qss_a_00049","is_oa":true,"landing_page_url":"https://doi.org/10.1162/qss_a_00049","pdf_url":"https://direct.mit.edu/qss/article-pdf/1/2/525/1885831/qss_a_00049.pdf","source":{"id":"https://openalex.org/S4210195326","display_name":"Quantitative Science Studies","issn_l":"2641-3337","issn":["2641-3337"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT 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":"Quantitative Science Studies","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:d0a2d6f5529d425aa251dd76f370dd86","is_oa":true,"landing_page_url":"https://doaj.org/article/d0a2d6f5529d425aa251dd76f370dd86","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Quantitative Science Studies (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/qss_a_00049","is_oa":true,"landing_page_url":"https://doi.org/10.1162/qss_a_00049","pdf_url":"https://direct.mit.edu/qss/article-pdf/1/2/525/1885831/qss_a_00049.pdf","source":{"id":"https://openalex.org/S4210195326","display_name":"Quantitative Science Studies","issn_l":"2641-3337","issn":["2641-3337"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT 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":"Quantitative Science Studies","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3024646987.pdf","grobid_xml":"https://content.openalex.org/works/W3024646987.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W54887220","https://openalex.org/W87847351","https://openalex.org/W636844128","https://openalex.org/W1485293642","https://openalex.org/W1498436455","https://openalex.org/W1522301498","https://openalex.org/W1537310530","https://openalex.org/W1712168991","https://openalex.org/W2056132907","https://openalex.org/W2059503205","https://openalex.org/W2064675550","https://openalex.org/W2098368939","https://openalex.org/W2101234009","https://openalex.org/W2107915309","https://openalex.org/W2146241755","https://openalex.org/W2274116681","https://openalex.org/W2736387275","https://openalex.org/W2781044713","https://openalex.org/W2890222814","https://openalex.org/W2893284381","https://openalex.org/W2896146129","https://openalex.org/W2911964244","https://openalex.org/W2950133940","https://openalex.org/W3122576567","https://openalex.org/W4245616207"],"related_works":["https://openalex.org/W2076543106","https://openalex.org/W2523437662","https://openalex.org/W89844371","https://openalex.org/W2019891950","https://openalex.org/W2085842814","https://openalex.org/W4286643620","https://openalex.org/W4387048144","https://openalex.org/W2492135063","https://openalex.org/W2362514456","https://openalex.org/W2136232598"],"abstract_inverted_index":{"Many":[0],"interesting":[1],"use":[2],"cases":[3],"of":[4,22,42,49,73,83,94,122,131,137],"research":[5,11,74,132],"data":[6,12,156],"classifiers":[7],"presuppose":[8],"that":[9],"a":[10,43,81],"item":[13],"can":[14,110],"be":[15,111],"mapped":[16],"to":[17,87,118,127,143],"more":[18],"than":[19],"one":[20],"field":[21,136],"study,":[23,95],"but":[24],"for":[25,116,158,163],"such":[26],"classification":[27,55],"mechanisms,":[28],"reproducible":[29],"evaluations":[30],"are":[31,161],"lacking.":[32],"This":[33],"paper":[34],"closes":[35],"this":[36],"gap:":[37],"It":[38],"describes":[39],"the":[40,70,148,155],"creation":[41],"training":[44,160],"and":[45,57,78,154],"evaluation":[46],"set":[47,82],"comprised":[48],"labeled":[50],"metadata,":[51],"evaluates":[52],"several":[53],"supervised":[54],"approaches,":[56],"comments":[58],"on":[59],"their":[60,159],"application":[61],"in":[62,113,146],"scientometric":[63,114],"research.":[64],"The":[65,108,150],"metadata":[66],"were":[67],"retrieved":[68],"from":[69],"DataCite":[71],"index":[72],"data,":[75,133],"pre":[76],"processed,":[77],"compiled":[79],"into":[80],"613,585":[84],"records.":[85],"According":[86],"our":[88],"experiments":[89],"with":[90],"20":[91],"general":[92],"fields":[93],"multi":[96],"layer":[97],"perceptron":[98],"models":[99,109,153],"perform":[100],"best,":[101],"followed":[102],"by":[103,135],"long":[104],"short-term":[105],"memory":[106],"models.":[107,149],"used":[112,157],"research,":[115],"example":[117],"analyze":[119],"interdisciplinary":[120],"trends":[121],"digital":[123],"scholarly":[124],"output":[125],"or":[126],"characterize":[128],"growth":[129],"patterns":[130],"stratified":[134],"study.":[138],"Our":[139],"findings":[140],"allow":[141],"us":[142],"estimate":[144],"errors":[145],"applying":[147],"best":[151],"performing":[152],"available":[162],"re":[164],"use.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}