{"id":"https://openalex.org/W4205624944","doi":"https://doi.org/10.1109/bigdata52589.2021.9671611","title":"Computational Curation and the Application of Large-Scale Vocabularies","display_name":"Computational Curation and the Application of Large-Scale Vocabularies","publication_year":2021,"publication_date":"2021-12-15","ids":{"openalex":"https://openalex.org/W4205624944","doi":"https://doi.org/10.1109/bigdata52589.2021.9671611"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata52589.2021.9671611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671611","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-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/A5051739817","display_name":"Sam Grabus","orcid":"https://orcid.org/0000-0003-4670-5690"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sam Grabus","raw_affiliation_strings":["MRC, College of Computing & Informatics, Drexel University, Philadelphia, USA"],"affiliations":[{"raw_affiliation_string":"MRC, College of Computing & Informatics, Drexel University, Philadelphia, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035913440","display_name":"Jane Greenberg","orcid":"https://orcid.org/0000-0001-7819-5360"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jane Greenberg","raw_affiliation_strings":["MRC, College of Computing & Informatics, Drexel University, Philadelphia, USA"],"affiliations":[{"raw_affiliation_string":"MRC, College of Computing & Informatics, Drexel University, Philadelphia, USA","institution_ids":["https://openalex.org/I72816309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5051739817"],"corresponding_institution_ids":["https://openalex.org/I72816309"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.18508132,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2220","last_page":"2223"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9983000159263611,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9983000159263611,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9940999746322632,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/lemmatisation","display_name":"Lemmatisation","score":0.8567376136779785},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8239865303039551},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.776978611946106},{"id":"https://openalex.org/keywords/encyclopedia","display_name":"Encyclopedia","score":0.6352359056472778},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.6168116331100464},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5621086359024048},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5599692463874817},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5531430244445801},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.5366799831390381},{"id":"https://openalex.org/keywords/controlled-vocabulary","display_name":"Controlled vocabulary","score":0.47733765840530396},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.456308513879776},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4464011490345001},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.39166131615638733},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3865269124507904},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3320550322532654},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1960425078868866}],"concepts":[{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.8567376136779785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8239865303039551},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.776978611946106},{"id":"https://openalex.org/C148863701","wikidata":"https://www.wikidata.org/wiki/Q5292","display_name":"Encyclopedia","level":2,"score":0.6352359056472778},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.6168116331100464},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5621086359024048},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5599692463874817},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5531430244445801},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5366799831390381},{"id":"https://openalex.org/C110615152","wikidata":"https://www.wikidata.org/wiki/Q1469824","display_name":"Controlled vocabulary","level":2,"score":0.47733765840530396},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.456308513879776},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4464011490345001},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.39166131615638733},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3865269124507904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3320550322532654},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1960425078868866},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata52589.2021.9671611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671611","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1577197834","https://openalex.org/W2037943133","https://openalex.org/W2473380090","https://openalex.org/W2553758616","https://openalex.org/W2768946745","https://openalex.org/W2910098727","https://openalex.org/W2912055463","https://openalex.org/W2955329901","https://openalex.org/W3008344928","https://openalex.org/W3212558890","https://openalex.org/W4245628022","https://openalex.org/W4293159471"],"related_works":["https://openalex.org/W2348562996","https://openalex.org/W4387776128","https://openalex.org/W3010321750","https://openalex.org/W4394774294","https://openalex.org/W3159833212","https://openalex.org/W2887281027","https://openalex.org/W4244686159","https://openalex.org/W2137937634","https://openalex.org/W2146486983","https://openalex.org/W2101373085"],"abstract_inverted_index":{"Paper":[0],"presents":[1],"an":[2],"exploratory":[3],"case":[4],"study":[5],"comparing":[6],"stemming":[7,39],"and":[8,29,52],"lemmatization":[9,45],"results":[10,25,46],"for":[11,65],"the":[12,54],"automatic":[13,62],"application":[14],"of":[15],"large-scale":[16],"controlled":[17],"vocabularies":[18],"processed":[19],"against":[20],"archival":[21,66],"encyclopedia":[22],"entries.":[23],"The":[24],"report":[26],"relative":[27,43],"recall":[28],"precision":[30],"evaluations":[31],"across":[32],"both":[33],"results.":[34],"Research":[35],"shows":[36],"that":[37],"while":[38],"has":[40],"a":[41,48],"higher":[42,49],"recall,":[44],"in":[47],"relevance":[50],"score":[51],"eliminates":[53],"over-stemming":[55],"challenges.":[56],"Results":[57],"provide":[58],"insight":[59],"into":[60],"improving":[61],"curation":[63],"workflows":[64],"resources.":[67]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}