{"id":"https://openalex.org/W3035468365","doi":"https://doi.org/10.1145/3371925","title":"Anatomy of Metadata for Data Curation","display_name":"Anatomy of Metadata for Data Curation","publication_year":2020,"publication_date":"2020-06-13","ids":{"openalex":"https://openalex.org/W3035468365","doi":"https://doi.org/10.1145/3371925","mag":"3035468365"},"language":"en","primary_location":{"id":"doi:10.1145/3371925","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3371925","pdf_url":null,"source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data and Information Quality","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/A5108549027","display_name":"Larysa Visengeriyeva","orcid":null},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Larysa Visengeriyeva","raw_affiliation_strings":["TU Berlin"],"affiliations":[{"raw_affiliation_string":"TU Berlin","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009128577","display_name":"Ziawasch Abedjan","orcid":"https://orcid.org/0000-0002-2846-1373"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ziawasch Abedjan","raw_affiliation_strings":["TU Berlin"],"affiliations":[{"raw_affiliation_string":"TU Berlin","institution_ids":["https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5108549027"],"corresponding_institution_ids":["https://openalex.org/I4577782"],"apc_list":null,"apc_paid":null,"fwci":2.6928,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.90456814,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"12","issue":"3","first_page":"1","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9868000149726868,"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/T12034","display_name":"Digital and Cyber Forensics","score":0.9861000180244446,"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":0.9634948372840881},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8609358072280884},{"id":"https://openalex.org/keywords/data-element","display_name":"Data element","score":0.7434138059616089},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.6836199760437012},{"id":"https://openalex.org/keywords/meta-data-services","display_name":"Meta Data Services","score":0.6060410737991333},{"id":"https://openalex.org/keywords/metadata-modeling","display_name":"Metadata modeling","score":0.5977342128753662},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5299219489097595},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.5000214576721191},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.48558682203292847},{"id":"https://openalex.org/keywords/geospatial-metadata","display_name":"Geospatial metadata","score":0.4815264344215393},{"id":"https://openalex.org/keywords/data-mapping","display_name":"Data mapping","score":0.4571797847747803},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4529910385608673},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2734084129333496},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2548675835132599},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.06864580512046814}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.9634948372840881},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8609358072280884},{"id":"https://openalex.org/C30872290","wikidata":"https://www.wikidata.org/wiki/Q1172389","display_name":"Data element","level":3,"score":0.7434138059616089},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.6836199760437012},{"id":"https://openalex.org/C136976847","wikidata":"https://www.wikidata.org/wiki/Q6822297","display_name":"Meta Data Services","level":4,"score":0.6060410737991333},{"id":"https://openalex.org/C110326360","wikidata":"https://www.wikidata.org/wiki/Q17149476","display_name":"Metadata modeling","level":4,"score":0.5977342128753662},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5299219489097595},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.5000214576721191},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.48558682203292847},{"id":"https://openalex.org/C193150823","wikidata":"https://www.wikidata.org/wiki/Q1477538","display_name":"Geospatial metadata","level":5,"score":0.4815264344215393},{"id":"https://openalex.org/C137314826","wikidata":"https://www.wikidata.org/wiki/Q2330408","display_name":"Data mapping","level":2,"score":0.4571797847747803},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4529910385608673},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2734084129333496},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2548675835132599},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.06864580512046814},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3371925","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3371925","pdf_url":null,"source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data and Information Quality","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W108763474","https://openalex.org/W153094444","https://openalex.org/W192214595","https://openalex.org/W760598031","https://openalex.org/W1502624642","https://openalex.org/W1521736627","https://openalex.org/W1522984953","https://openalex.org/W1610496399","https://openalex.org/W1984566373","https://openalex.org/W1987787956","https://openalex.org/W1991137221","https://openalex.org/W1992479406","https://openalex.org/W2020498246","https://openalex.org/W2023052779","https://openalex.org/W2026493302","https://openalex.org/W2038412523","https://openalex.org/W2044022210","https://openalex.org/W2044469685","https://openalex.org/W2046298800","https://openalex.org/W2046793639","https://openalex.org/W2058049456","https://openalex.org/W2064766209","https://openalex.org/W2081186682","https://openalex.org/W2099637074","https://openalex.org/W2113411758","https://openalex.org/W2122323423","https://openalex.org/W2122949840","https://openalex.org/W2126848435","https://openalex.org/W2137130182","https://openalex.org/W2151310484","https://openalex.org/W2161702708","https://openalex.org/W2164187405","https://openalex.org/W2213275763","https://openalex.org/W2232417456","https://openalex.org/W2240592568","https://openalex.org/W2295468252","https://openalex.org/W2298871042","https://openalex.org/W2331052961","https://openalex.org/W2334523061","https://openalex.org/W2421097601","https://openalex.org/W2435238507","https://openalex.org/W2438792749","https://openalex.org/W2518164973","https://openalex.org/W2544486974","https://openalex.org/W2574683263","https://openalex.org/W2591700809","https://openalex.org/W2612744932","https://openalex.org/W2767992112","https://openalex.org/W2769041395","https://openalex.org/W2790130692","https://openalex.org/W2794670651","https://openalex.org/W2808833850","https://openalex.org/W2875652255","https://openalex.org/W2893303656","https://openalex.org/W2943955885","https://openalex.org/W2948145720","https://openalex.org/W2959716049","https://openalex.org/W4232478844","https://openalex.org/W4293162521","https://openalex.org/W6636177537"],"related_works":["https://openalex.org/W2374379029","https://openalex.org/W3084772717","https://openalex.org/W3199469221","https://openalex.org/W2362378919","https://openalex.org/W1987988355","https://openalex.org/W2353291710","https://openalex.org/W2373546426","https://openalex.org/W2958831360","https://openalex.org/W2796209520","https://openalex.org/W2349328164"],"abstract_inverted_index":{"Real-world":[0],"datasets":[1],"often":[2],"suffer":[3],"from":[4],"various":[5],"data":[6,10,19,42,45,60,74,126],"quality":[7,75,127],"problems.":[8],"Several":[9],"cleaning":[11,20],"solutions":[12],"have":[13],"been":[14],"proposed":[15],"so":[16],"far.":[17],"However,":[18],"remains":[21],"a":[22,67,88,92,111],"manual":[23],"and":[24,30,59,77,82,100],"iterative":[25],"task":[26],"that":[27,69,95],"requires":[28],"domain":[29],"technical":[31],"expertise.":[32],"Exploiting":[33],"metadata":[34,58,79,99,124],"promises":[35],"to":[36,113],"improve":[37],"the":[38,54,71,102,115,119],"tedious":[39],"process":[40],"of":[41,104,107,118],"preparation,":[43],"because":[44],"errors":[46],"are":[47],"detectable":[48],"through":[49],"metadata.":[50,108],"This":[51],"article":[52],"investigates":[53],"intrinsic":[55],"connection":[56,72],"between":[57,73],"errors.":[61],"In":[62],"this":[63],"work,":[64],"we":[65,86],"establish":[66],"mapping":[68],"reflects":[70],"issues":[76],"extractable":[78],"using":[80],"qualitative":[81],"quantitative":[83],"techniques.":[84],"Additionally,":[85],"present":[87],"taxonomy":[89],"based":[90],"on":[91],"closed":[93],"grammar":[94,120],"covers":[96],"all":[97],"existing":[98],"allows":[101],"composition":[103],"novel":[105],"types":[106],"We":[109],"provide":[110],"case-study":[112],"show":[114],"practical":[116],"application":[117],"for":[121,125],"generating":[122],"new":[123],"assessment.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
