{"id":"https://openalex.org/W3158136190","doi":"https://doi.org/10.3233/ds-210035","title":"Automatic de-identification of data download packages","display_name":"Automatic de-identification of data download packages","publication_year":2021,"publication_date":"2021-09-07","ids":{"openalex":"https://openalex.org/W3158136190","doi":"https://doi.org/10.3233/ds-210035","mag":"3158136190"},"language":"en","primary_location":{"id":"doi:10.3233/ds-210035","is_oa":true,"landing_page_url":"https://doi.org/10.3233/ds-210035","pdf_url":"https://content.iospress.com:443/download/data-science/ds210035?id=data-science%2Fds210035","source":{"id":"https://openalex.org/S4210178722","display_name":"Data Science","issn_l":"2451-8484","issn":["2451-8484","2451-8492"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS 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 Science","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://content.iospress.com:443/download/data-science/ds210035?id=data-science%2Fds210035","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021589283","display_name":"Laura Boeschoten","orcid":"https://orcid.org/0000-0002-3536-0474"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Laura Boeschoten","raw_affiliation_strings":["Department of Methodology and Statistics, Utrecht University, Utrecht, The Netherlands. E-mail:\u00a0l.boeschoten@uu.nl"],"raw_orcid":"https://orcid.org/0000-0002-3536-0474","affiliations":[{"raw_affiliation_string":"Department of Methodology and Statistics, Utrecht University, Utrecht, The Netherlands. E-mail:\u00a0l.boeschoten@uu.nl","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025790809","display_name":"Roos Voorvaart","orcid":"https://orcid.org/0000-0002-4411-8495"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Roos Voorvaart","raw_affiliation_strings":["Research and Data Management Services, Utrecht University, Utrecht, The Netherlands. E-mail:\u00a0r.voorvaart@uu.nl"],"raw_orcid":"https://orcid.org/0000-0002-4411-8495","affiliations":[{"raw_affiliation_string":"Research and Data Management Services, Utrecht University, Utrecht, The Netherlands. E-mail:\u00a0r.voorvaart@uu.nl","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001031334","display_name":"Ruben van den Goorbergh","orcid":"https://orcid.org/0000-0003-3229-3015"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ruben Van Den Goorbergh","raw_affiliation_strings":["Department of Methodology and Statistics, Utrecht University, Utrecht, The Netherlands. E-mail:\u00a0r.vandengoorbergh@uu.nl"],"raw_orcid":"https://orcid.org/0000-0003-3229-3015","affiliations":[{"raw_affiliation_string":"Department of Methodology and Statistics, Utrecht University, Utrecht, The Netherlands. E-mail:\u00a0r.vandengoorbergh@uu.nl","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061950675","display_name":"Casper Kaandorp","orcid":"https://orcid.org/0000-0001-6326-6680"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Casper Kaandorp","raw_affiliation_strings":["Research and Data Management Services, Utrecht University, Utrecht, The Netherlands. E-mail:\u00a0c.s.kaandorp@uu.nl"],"raw_orcid":"https://orcid.org/0000-0001-6326-6680","affiliations":[{"raw_affiliation_string":"Research and Data Management Services, Utrecht University, Utrecht, The Netherlands. E-mail:\u00a0c.s.kaandorp@uu.nl","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101927253","display_name":"Martine de Vos","orcid":"https://orcid.org/0000-0001-5301-1713"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Martine De Vos","raw_affiliation_strings":["Research and Data Management Services, Utrecht University, Utrecht, The Netherlands. E-mail:\u00a0m.g.devos@uu.nl"],"raw_orcid":"https://orcid.org/0000-0001-5301-1713","affiliations":[{"raw_affiliation_string":"Research and Data Management Services, Utrecht University, Utrecht, The Netherlands. E-mail:\u00a0m.g.devos@uu.nl","institution_ids":["https://openalex.org/I193662353"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5021589283"],"corresponding_institution_ids":["https://openalex.org/I193662353"],"apc_list":null,"apc_paid":null,"fwci":0.1399,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53240967,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"4","issue":"2","first_page":"101","last_page":"120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9998999834060669,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9998999834060669,"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/T11045","display_name":"Privacy, Security, and Data Protection","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12034","display_name":"Digital and Cyber Forensics","score":0.9969000220298767,"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/download","display_name":"Download","score":0.8031520843505859},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6421686410903931},{"id":"https://openalex.org/keywords/file-format","display_name":"File format","score":0.6378603577613831},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.6286333799362183},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6067872047424316},{"id":"https://openalex.org/keywords/treasure","display_name":"Treasure","score":0.5864839553833008},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.47429564595222473},{"id":"https://openalex.org/keywords/data-file","display_name":"Data file","score":0.42698320746421814},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.37531578540802},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33158692717552185},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3282145857810974},{"id":"https://openalex.org/keywords/internet-privacy","display_name":"Internet privacy","score":0.3232962489128113},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11100080609321594}],"concepts":[{"id":"https://openalex.org/C2780154274","wikidata":"https://www.wikidata.org/wiki/Q7126717","display_name":"Download","level":2,"score":0.8031520843505859},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6421686410903931},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.6378603577613831},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.6286333799362183},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6067872047424316},{"id":"https://openalex.org/C2776084483","wikidata":"https://www.wikidata.org/wiki/Q272937","display_name":"Treasure","level":2,"score":0.5864839553833008},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.47429564595222473},{"id":"https://openalex.org/C171730128","wikidata":"https://www.wikidata.org/wiki/Q5227290","display_name":"Data file","level":2,"score":0.42698320746421814},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.37531578540802},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33158692717552185},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3282145857810974},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.3232962489128113},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11100080609321594},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","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},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3233/ds-210035","is_oa":true,"landing_page_url":"https://doi.org/10.3233/ds-210035","pdf_url":"https://content.iospress.com:443/download/data-science/ds210035?id=data-science%2Fds210035","source":{"id":"https://openalex.org/S4210178722","display_name":"Data Science","issn_l":"2451-8484","issn":["2451-8484","2451-8492"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS 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 Science","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2105.02175","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.02175","pdf_url":"https://arxiv.org/pdf/2105.02175","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3158136190","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2105.02175.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:dspace.library.uu.nl:1874/415754","is_oa":true,"landing_page_url":"https://dspace.library.uu.nl/handle/1874/415754","pdf_url":null,"source":{"id":"https://openalex.org/S4306401649","display_name":"Utrecht University Repository (Utrecht University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193662353","host_organization_name":"Utrecht University","host_organization_lineage":["https://openalex.org/I193662353"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Contribution to conference"},{"id":"doi:10.48550/arxiv.2105.02175","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2105.02175","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.3233/ds-210035","is_oa":true,"landing_page_url":"https://doi.org/10.3233/ds-210035","pdf_url":"https://content.iospress.com:443/download/data-science/ds210035?id=data-science%2Fds210035","source":{"id":"https://openalex.org/S4210178722","display_name":"Data Science","issn_l":"2451-8484","issn":["2451-8484","2451-8492"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS 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 Science","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.4099999964237213}],"awards":[{"id":"https://openalex.org/G6221045140","display_name":"Advancing social science with valid measures derived from incidental data","funder_award_id":"VI.Vidi.195.152","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321010","display_name":"Universiteit Utrecht","ror":"https://ror.org/04pp8hn57"},{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3158136190.pdf","grobid_xml":"https://content.openalex.org/works/W3158136190.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W77869065","https://openalex.org/W1913989311","https://openalex.org/W1979492569","https://openalex.org/W2004710253","https://openalex.org/W2099249232","https://openalex.org/W2135930857","https://openalex.org/W2137036358","https://openalex.org/W2159024459","https://openalex.org/W2160987310","https://openalex.org/W2163263459","https://openalex.org/W2252031683","https://openalex.org/W2314398369","https://openalex.org/W2341528187","https://openalex.org/W2478460150","https://openalex.org/W2561773199","https://openalex.org/W2605982830","https://openalex.org/W2744160972","https://openalex.org/W2904573504","https://openalex.org/W2951152347","https://openalex.org/W2974738913","https://openalex.org/W3004227146","https://openalex.org/W3023236086","https://openalex.org/W3092884751","https://openalex.org/W3098185008","https://openalex.org/W3101998545","https://openalex.org/W3119911073","https://openalex.org/W6675354045","https://openalex.org/W6716166186","https://openalex.org/W6772180295","https://openalex.org/W6927473512"],"related_works":["https://openalex.org/W2617437670","https://openalex.org/W2343063361","https://openalex.org/W2056918045","https://openalex.org/W1865735054","https://openalex.org/W2563176732","https://openalex.org/W2549065936","https://openalex.org/W2582478289","https://openalex.org/W1460225616","https://openalex.org/W1981764722","https://openalex.org/W2184205387","https://openalex.org/W2132439641","https://openalex.org/W1966583887","https://openalex.org/W922504128","https://openalex.org/W2980473938","https://openalex.org/W2035463494","https://openalex.org/W1502598440","https://openalex.org/W94744212","https://openalex.org/W2358131491","https://openalex.org/W2341503649","https://openalex.org/W3029871829"],"abstract_inverted_index":{"The":[0,25],"General":[1],"Data":[2,47],"Protection":[3],"Regulation":[4],"(GDPR)":[5],"grants":[6],"all":[7,54],"natural":[8],"persons":[9],"the":[10,32,41,63,79,87,136,139,144],"right":[11],"to":[12,30,107],"access":[13],"their":[14,94],"personal":[15],"data":[16,23,26,33,42,55,80],"if":[17],"this":[18],"is":[19,105],"being":[20],"processed":[21],"by":[22,57],"controllers.":[24],"controllers":[27],"are":[28],"obliged":[29],"share":[31],"in":[34,43],"an":[35],"electronic":[36],"format":[37],"and":[38,59,70,120,129,141],"often":[39],"provide":[40],"a":[44,66,72,101],"so":[45],"called":[46],"Download":[48],"Package":[49],"(DDP).":[50],"These":[51,113],"DDPs":[52,95],"contain":[53],"collected":[56],"public":[58],"private":[60,130],"entities":[61],"during":[62],"course":[64],"of":[65,89,111,138],"citizens\u2019":[67],"digital":[68],"life":[69],"form":[71],"treasure":[73],"trove":[74],"for":[75,96],"social":[76],"scientists.":[77],"However,":[78],"can":[81,146],"be":[82,147],"deeply":[83],"private.":[84],"To":[85],"protect":[86],"privacy":[88],"research":[90],"participants":[91],"while":[92],"using":[93],"scientific":[97],"research,":[98],"we":[99],"developed":[100],"de-identification":[102],"algorithm":[103,140,145],"that":[104],"able":[106],"handle":[108],"typical":[109],"characteristics":[110],"DDPs.":[112],"include":[114],"regularly":[115],"changing":[116],"file":[117,124,127],"structures,":[118],"visual":[119],"textual":[121],"content,":[122],"differing":[123,126],"formats,":[125],"structures":[128],"information":[131],"like":[132],"usernames.":[133],"We":[134],"investigate":[135],"performance":[137],"illustrate":[142],"how":[143],"tailored":[148],"towards":[149],"specific":[150],"DDP":[151],"structures.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}
