{"id":"https://openalex.org/W3047587672","doi":null,"title":"Data Anonymization using Machine Learning and Natural Language Processing","display_name":"Data Anonymization using Machine Learning and Natural Language Processing","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3047587672","mag":"3047587672"},"language":"en","primary_location":{"id":"pmh:oai:lup-student-papers.lub.lu.se:9024789","doi":null,"is_oa":true,"landing_page_url":"http://lup.lub.lu.se/student-papers/record/9024789","pdf_url":"http://lup.lub.lu.se/student-papers/record/9024789","source":{"id":"https://openalex.org/S4306402420","display_name":"Lund University Publications Student Papers (Lund University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I187531555","host_organization_name":"Lund University","host_organization_lineage":["https://openalex.org/I187531555"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"H2"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://lup.lub.lu.se/student-papers/record/9024789","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074724343","display_name":"John Helbrink","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John Helbrink","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5008352628","display_name":"Simon \u00c5kesson","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simon \u00c5kesson","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9574999809265137,"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":0.9574999809265137,"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/T10028","display_name":"Topic Modeling","score":0.023900000378489494,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.0027000000700354576,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-anonymization","display_name":"data anonymization","score":0.9869999885559082},{"id":"https://openalex.org/keywords/personally-identifiable-information","display_name":"personally identifiable information","score":0.7490000128746033},{"id":"https://openalex.org/keywords/gdpr","display_name":"GDPR","score":0.6349999904632568},{"id":"https://openalex.org/keywords/bidirectional-lstm","display_name":"bidirectional LSTM","score":0.9100000262260437},{"id":"https://openalex.org/keywords/contextualized-embeddings","display_name":"contextual embeddings","score":0.7590000033378601},{"id":"https://openalex.org/keywords/conditional-random-fields","display_name":"conditional random fields","score":0.9660000205039978},{"id":"https://openalex.org/keywords/neural-network-architecture","display_name":"neural network architecture","score":0.7300000190734863},{"id":"https://openalex.org/keywords/human-oversight","display_name":"human oversight","score":0.5239999890327454},{"id":"https://openalex.org/keywords/information-exposure","display_name":"information exposure","score":0.46399998664855957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7127658724784851},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5294392108917236},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.44415247440338135},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4300442636013031},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3304779529571533},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08491897583007812},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:lup-student-papers.lub.lu.se:9024789","doi":null,"is_oa":true,"landing_page_url":"http://lup.lub.lu.se/student-papers/record/9024789","pdf_url":"http://lup.lub.lu.se/student-papers/record/9024789","source":{"id":"https://openalex.org/S4306402420","display_name":"Lund University Publications Student Papers (Lund University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I187531555","host_organization_name":"Lund University","host_organization_lineage":["https://openalex.org/I187531555"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"H2"},{"id":"mag:3047587672","doi":null,"is_oa":false,"landing_page_url":"http://lup.lub.lu.se/student-papers/record/9024789/file/9024790.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:lup-student-papers.lub.lu.se:9024789","doi":null,"is_oa":true,"landing_page_url":"http://lup.lub.lu.se/student-papers/record/9024789","pdf_url":"http://lup.lub.lu.se/student-papers/record/9024789","source":{"id":"https://openalex.org/S4306402420","display_name":"Lund University Publications Student Papers (Lund University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I187531555","host_organization_name":"Lund University","host_organization_lineage":["https://openalex.org/I187531555"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"H2"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3047587672.pdf","grobid_xml":"https://content.openalex.org/works/W3047587672.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W1623072288","https://openalex.org/W2040870580","https://openalex.org/W2117772341","https://openalex.org/W2144578941","https://openalex.org/W2250539671","https://openalex.org/W2970971581"],"related_works":["https://openalex.org/W4287779419","https://openalex.org/W3201979047","https://openalex.org/W2889497599","https://openalex.org/W7124834137","https://openalex.org/W7036573251","https://openalex.org/W6908707665","https://openalex.org/W3197112885","https://openalex.org/W3088703576","https://openalex.org/W7064386791","https://openalex.org/W3031013112"],"abstract_inverted_index":{"With":[0],"the":[1,4,10,55,87,95,103,120,123,125,136],"introduction":[2],"of":[3,24,97,105,122,132,138],"General":[5],"Data":[6],"Protection":[7],"Regulation":[8],"(GDPR)":[9],"demand":[11],"to":[12,28,43,117],"protect":[13],"personal":[14],"identi":[15],"able":[16],"information":[17,140],"from":[18],"unnecessary":[19,139],"exposure":[20],"is":[21,27],"growing.The":[22],"objective":[23],"this":[25],"thesis":[26],"explore":[29],"and":[30,40,51,59,66,78],"construct":[31],"a":[32,68],"system":[33,127],"that":[34],"will":[35,46,111],"use":[36],"natural":[37],"language":[38],"processing":[39],"machine":[41],"learning":[42],"anonymize":[44],"data.This":[45],"provide":[47],"further":[48],"analysis":[49],"opportunities":[50],"additional":[52],"protection":[53],"for":[54,115],"individual":[56],"person.We":[57],"implemented":[58],"compared":[60],"di":[61],"erent":[62],"neural":[63],"network":[64,73],"architectures":[65],"frameworks.Using":[67],"bidirectional":[69],"Long":[70],"Short-Term":[71],"Memory":[72],"together":[74],"with":[75,86],"contextualized":[76],"embeddings":[77],"conditional":[79],"random":[80],"elds,":[81],"state-of-the-art":[82],"results":[83],"were":[84],"reached":[85],"best":[88],"F":[89],"1":[90],"score":[91],"at":[92],".%.This":[93],"shows":[94],"importance":[96],"contextual":[98],"awareness":[99],"as":[100,102],"well":[101],"impact":[104],"pretrained":[106],"word":[107],"embeddings.However,":[108],"human":[109],"supervision":[110],"still":[112],"be":[113],"needed":[114],"it":[116],"completely":[118],"guarantee":[119],"anonymization":[121],"messages.Ultimately,":[124],"resulting":[126],"ful":[128],"lls":[129],"its":[130],"purpose":[131],"masking":[133],"texts,":[134],"removing":[135],"risk":[137],"exposure.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-27T15:51:10.671819","created_date":"2020-08-10T00:00:00"}