{"id":"https://openalex.org/W4297520131","doi":"https://doi.org/10.1162/dint_a_00162","title":"Automated metadata annotation: What is and is not possible with machine learning","display_name":"Automated metadata annotation: What is and is not possible with machine learning","publication_year":2022,"publication_date":"2022-09-28","ids":{"openalex":"https://openalex.org/W4297520131","doi":"https://doi.org/10.1162/dint_a_00162"},"language":"en","primary_location":{"id":"doi:10.1162/dint_a_00162","is_oa":true,"landing_page_url":"https://doi.org/10.1162/dint_a_00162","pdf_url":"https://direct.mit.edu/dint/article-pdf/doi/10.1162/dint_a_00162/2070161/dint_a_00162.pdf","source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"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":"Data Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/dint/article-pdf/doi/10.1162/dint_a_00162/2070161/dint_a_00162.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053083952","display_name":"Mingfang Wu","orcid":"https://orcid.org/0000-0003-1206-3431"},"institutions":[{"id":"https://openalex.org/I4210128169","display_name":"Australian Research Data Commons","ror":"https://ror.org/038sjwq14","country_code":"AU","type":"other","lineage":["https://openalex.org/I4210128169"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mingfang Wu","raw_affiliation_strings":["Australian Research Data Commons, Australian Research Data Commons, Melbourne, Australia, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Research Data Commons, Australian Research Data Commons, Melbourne, Australia, Australia","institution_ids":["https://openalex.org/I4210128169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025054635","display_name":"Hans Brandhorst","orcid":"https://orcid.org/0000-0001-8403-3552"},"institutions":[{"id":"https://openalex.org/I4210105103","display_name":"Foundation Centrum '45","ror":"https://ror.org/01cwg1p04","country_code":"NL","type":"healthcare","lineage":["https://openalex.org/I4210105103"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Hans Brandhorst","raw_affiliation_strings":["Iconclass, Voorscoten, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iconclass, Voorscoten, The Netherlands","institution_ids":["https://openalex.org/I4210105103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006661351","display_name":"Maria-Cristina Marinescu","orcid":"https://orcid.org/0000-0002-6978-2974"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Maria-Cristina Marinescu","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010943830","display_name":"Joaquim Mor\u00e9","orcid":"https://orcid.org/0000-0001-5432-0657"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Joaquim More Lopez","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086740311","display_name":"Margorie Hlava","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160724","display_name":"Access Technologies","ror":"https://ror.org/05kt92j68","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210160724"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Margorie Hlava","raw_affiliation_strings":["Access Innovations, Albuquerque, New Mexico, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Access Innovations, Albuquerque, New Mexico, USA","institution_ids":["https://openalex.org/I4210160724"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040513134","display_name":"Joseph D. Busch","orcid":"https://orcid.org/0000-0003-4775-8225"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Joseph Busch","raw_affiliation_strings":["Taxonomy Strategies, Washington, DC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taxonomy Strategies, Washington, DC, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5040513134"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1312,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.88751665,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"5","issue":"1","first_page":"122","last_page":"138"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12981","display_name":"Conservation Techniques and Studies","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/1206","display_name":"Conservation"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12364","display_name":"Archaeological Research and Protection","score":0.9843000173568726,"subfield":{"id":"https://openalex.org/subfields/1912","display_name":"Space and Planetary Science"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.930160403251648},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.824105978012085},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7673231363296509},{"id":"https://openalex.org/keywords/interoperability","display_name":"Interoperability","score":0.5711308717727661},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5502786040306091},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5424734354019165},{"id":"https://openalex.org/keywords/cultural-heritage","display_name":"Cultural heritage","score":0.5040404200553894},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38674378395080566},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.36767417192459106},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3622261881828308},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33888494968414307}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.930160403251648},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.824105978012085},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7673231363296509},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.5711308717727661},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5502786040306091},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5424734354019165},{"id":"https://openalex.org/C60671577","wikidata":"https://www.wikidata.org/wiki/Q210272","display_name":"Cultural heritage","level":2,"score":0.5040404200553894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38674378395080566},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.36767417192459106},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3622261881828308},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33888494968414307},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1162/dint_a_00162","is_oa":true,"landing_page_url":"https://doi.org/10.1162/dint_a_00162","pdf_url":"https://direct.mit.edu/dint/article-pdf/doi/10.1162/dint_a_00162/2070161/dint_a_00162.pdf","source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"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":"Data Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:upcommons.upc.edu:2117/374724","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/374724","pdf_url":"https://upcommons.upc.edu/bitstreams/f1d1c9ee-59f3-414e-b253-14388ec3a92a/download","source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:doaj.org/article:0a1df58e7afa422f9156887df55acff8","is_oa":false,"landing_page_url":"https://doaj.org/article/0a1df58e7afa422f9156887df55acff8","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data Intelligence, Vol 5, Iss 1, Pp 122-138 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/dint_a_00162","is_oa":true,"landing_page_url":"https://doi.org/10.1162/dint_a_00162","pdf_url":"https://direct.mit.edu/dint/article-pdf/doi/10.1162/dint_a_00162/2070161/dint_a_00162.pdf","source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"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":"Data Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.7300000190734863,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4297520131.pdf"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W88642373","https://openalex.org/W1587734090","https://openalex.org/W1999404243","https://openalex.org/W2108598243","https://openalex.org/W2302501749","https://openalex.org/W2937423263","https://openalex.org/W2948676181","https://openalex.org/W3093547668","https://openalex.org/W3105625590","https://openalex.org/W3187475615","https://openalex.org/W4205463685","https://openalex.org/W4233925072","https://openalex.org/W6726480034","https://openalex.org/W6799165131"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2361861616","https://openalex.org/W2095118173","https://openalex.org/W2382021449","https://openalex.org/W2263699433","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W2377979023","https://openalex.org/W2093262417"],"abstract_inverted_index":{"ABSTRACT":[0],"Automated":[1],"metadata":[2,108],"annotation":[3,109],"is":[4,49,65,80],"only":[5],"as":[6,8,89],"good":[7],"training":[9],"dataset,":[10],"or":[11],"rules":[12],"that":[13,79],"are":[14,86,98],"available":[15,51,68],"for":[16,82],"the":[17,76,103],"domain.":[18],"It's":[19],"important":[20],"to":[21,37,52],"learn":[22],"what":[23,45],"type":[24,46],"of":[25,47,106],"data":[26],"content":[27,48,64],"a":[28],"pre-trained":[29],"machine":[30,83],"learning":[31],"algorithm":[32],"has":[33],"been":[34],"trained":[35],"on":[36],"understand":[38],"its":[39],"limitations":[40],"and":[41,57,62,72,91,113,122],"potential":[42],"biases.":[43],"Consider":[44],"readily":[50],"train":[53],"an":[54],"algorithm\u2014what's":[55],"popular":[56],"what's":[58],"available.":[59,99],"However,":[60],"scholarly":[61],"historical":[63],"often":[66],"not":[67],"in":[69,110],"consumable,":[70],"homogenized,":[71],"interoperable":[73],"formats":[74],"at":[75],"large":[77],"volume":[78],"required":[81],"learning.":[84],"There":[85],"exceptions":[87],"such":[88],"science":[90],"medicine,":[92],"where":[93],"large,":[94],"well":[95],"documented":[96],"collections":[97],"This":[100],"paper":[101],"presents":[102],"current":[104],"state":[105],"automated":[107],"cultural":[111],"heritage":[112],"research":[114],"data,":[115],"discusses":[116],"challenges":[117],"identified":[118],"from":[119],"use":[120],"cases,":[121],"proposes":[123],"solutions.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-22T09:01:20.584952","created_date":"2025-10-10T00:00:00"}
