{"id":"https://openalex.org/W4408472213","doi":"https://doi.org/10.1007/978-3-031-83472-1_9","title":"ClustEm4Ano: Clustering Text Embeddings of\u00a0Nominal Textual Attributes for\u00a0Microdata Anonymization","display_name":"ClustEm4Ano: Clustering Text Embeddings of\u00a0Nominal Textual Attributes for\u00a0Microdata Anonymization","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4408472213","doi":"https://doi.org/10.1007/978-3-031-83472-1_9"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-83472-1_9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-83472-1_9","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-83472-1_9.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-83472-1_9.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092737549","display_name":"Robert Aufschl\u00e4ger","orcid":"https://orcid.org/0009-0004-0986-3504"},"institutions":[{"id":"https://openalex.org/I83041830","display_name":"Deggendorf Institute of Technology","ror":"https://ror.org/02kw5st29","country_code":"DE","type":"education","lineage":["https://openalex.org/I83041830"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Robert Aufschl\u00e4ger","raw_affiliation_strings":["Deggendorf Institute of Technology, 94469, Deggendorf, Germany"],"raw_orcid":"https://orcid.org/0009-0004-0986-3504","affiliations":[{"raw_affiliation_string":"Deggendorf Institute of Technology, 94469, Deggendorf, Germany","institution_ids":["https://openalex.org/I83041830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047845225","display_name":"Sebastian Wilhelm","orcid":"https://orcid.org/0000-0002-4370-9234"},"institutions":[{"id":"https://openalex.org/I83041830","display_name":"Deggendorf Institute of Technology","ror":"https://ror.org/02kw5st29","country_code":"DE","type":"education","lineage":["https://openalex.org/I83041830"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Wilhelm","raw_affiliation_strings":["Deggendorf Institute of Technology, 94469, Deggendorf, Germany"],"raw_orcid":"https://orcid.org/0000-0002-4370-9234","affiliations":[{"raw_affiliation_string":"Deggendorf Institute of Technology, 94469, Deggendorf, Germany","institution_ids":["https://openalex.org/I83041830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052070648","display_name":"Michael Heigl","orcid":"https://orcid.org/0000-0001-7303-113X"},"institutions":[{"id":"https://openalex.org/I83041830","display_name":"Deggendorf Institute of Technology","ror":"https://ror.org/02kw5st29","country_code":"DE","type":"education","lineage":["https://openalex.org/I83041830"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Heigl","raw_affiliation_strings":["Deggendorf Institute of Technology, 94469, Deggendorf, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7303-113X","affiliations":[{"raw_affiliation_string":"Deggendorf Institute of Technology, 94469, Deggendorf, Germany","institution_ids":["https://openalex.org/I83041830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056684537","display_name":"Martin Schramm","orcid":"https://orcid.org/0000-0001-6206-2969"},"institutions":[{"id":"https://openalex.org/I83041830","display_name":"Deggendorf Institute of Technology","ror":"https://ror.org/02kw5st29","country_code":"DE","type":"education","lineage":["https://openalex.org/I83041830"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Schramm","raw_affiliation_strings":["Deggendorf Institute of Technology, 94469, Deggendorf, Germany"],"raw_orcid":"https://orcid.org/0000-0001-6206-2969","affiliations":[{"raw_affiliation_string":"Deggendorf Institute of Technology, 94469, Deggendorf, Germany","institution_ids":["https://openalex.org/I83041830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5092737549"],"corresponding_institution_ids":["https://openalex.org/I83041830"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":7.2602,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.96928816,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"122","last_page":"137"},"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":0.9918000102043152,"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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9783999919891357,"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/microdata","display_name":"Microdata (statistics)","score":0.9289435148239136},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8802449107170105},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6707249879837036},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43350809812545776},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38667842745780945},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32568055391311646}],"concepts":[{"id":"https://openalex.org/C2778355071","wikidata":"https://www.wikidata.org/wiki/Q1933849","display_name":"Microdata (statistics)","level":4,"score":0.9289435148239136},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8802449107170105},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6707249879837036},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43350809812545776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38667842745780945},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32568055391311646},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C52130261","wikidata":"https://www.wikidata.org/wiki/Q39825","display_name":"Census","level":3,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-83472-1_9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-83472-1_9","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-83472-1_9.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-3-031-83472-1_9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-83472-1_9","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-83472-1_9.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4233054146","display_name":null,"funder_award_id":"16KISA128K","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4769925832","display_name":null,"funder_award_id":"19A23003H","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4408472213.pdf","grobid_xml":"https://content.openalex.org/works/W4408472213.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W69644699","https://openalex.org/W1988790447","https://openalex.org/W2016381774","https://openalex.org/W2030154491","https://openalex.org/W2090325367","https://openalex.org/W2119067110","https://openalex.org/W2128004504","https://openalex.org/W2128128412","https://openalex.org/W2134479759","https://openalex.org/W2136114025","https://openalex.org/W2142291269","https://openalex.org/W2150593711","https://openalex.org/W2161229593","https://openalex.org/W2250539671","https://openalex.org/W2304924924","https://openalex.org/W2528332618","https://openalex.org/W2559662148","https://openalex.org/W2614097854","https://openalex.org/W2911964244","https://openalex.org/W2912934387","https://openalex.org/W2970641574","https://openalex.org/W2982673177","https://openalex.org/W3016473712","https://openalex.org/W3021380283","https://openalex.org/W3043243165","https://openalex.org/W3175115403","https://openalex.org/W3198812502","https://openalex.org/W3204613796","https://openalex.org/W4205728856","https://openalex.org/W4212883601","https://openalex.org/W4386214310","https://openalex.org/W4386410523","https://openalex.org/W4386576685","https://openalex.org/W6675354045","https://openalex.org/W6748304040"],"related_works":["https://openalex.org/W3124882577","https://openalex.org/W2045945431","https://openalex.org/W3121353175","https://openalex.org/W2035955891","https://openalex.org/W4402137836","https://openalex.org/W3123218450","https://openalex.org/W4298259670","https://openalex.org/W3144851602","https://openalex.org/W141897957","https://openalex.org/W2241782923"],"abstract_inverted_index":{"Abstract":[0],"This":[1],"work":[2],"introduces":[3],",":[4],"an":[5],"anonymization":[6,16,92],"pipeline":[7,41],"that":[8,106],"can":[9,32,109,126],"be":[10,33],"used":[11,34],"for":[12,82,120],"generalization":[13,26],"and":[14,56,68,124],"suppression-based":[15],"of":[17,116,130],"nominal":[18],"textual":[19],"tabular":[20],"data.":[21],"It":[22],"automatically":[23],"generates":[24],"value":[25,48],"hierarchies":[27],"(VGHs)":[28],"that,":[29],"in":[30,38,114],"turn,":[31],"to":[35,44,99],"generalize":[36],"attributes":[37],"quasi-identifiers.":[39],"The":[40,84],"leverages":[42],"embeddings":[43,65],"generate":[45],"semantically":[46],"close":[47],"generalizations":[49],"through":[50],"iterative":[51],"clustering.":[52],"We":[53],"applied":[54],"KMeans":[55],"Hierarchical":[57],"Agglomerative":[58],"Clustering":[59],"on":[60,77],"13":[61],"different":[62],"predefined":[63],"text":[64],"(both":[66],"open":[67],"closed-source":[69],"(via":[70],"APIs)).":[71],"Our":[72,133],"approach":[73],"is":[74,135],"experimentally":[75],"tested":[76],"a":[78],"well-known":[79],"benchmark":[80],"dataset":[81],"anonymization:":[83],"UCI":[85],"Machine":[86],"Learning":[87],"Repository\u2019s":[88],"Adult":[89],"dataset.":[90],"supports":[91],"procedures":[93],"by":[94],"offering":[95],"more":[96],"possibilities":[97],"compared":[98],"using":[100],"arbitrarily":[101],"chosen":[102],"VGHs.":[103],"Experiments":[104],"demonstrate":[105],"these":[107],"VGHs":[108],"outperform":[110],"manually":[111],"constructed":[112],"ones":[113],"terms":[115],"downstream":[117],"efficacy":[118],"(especially":[119],"small":[121],"k":[122],"-anonymity)":[123],"therefore":[125],"foster":[127],"the":[128],"quality":[129],"anonymized":[131],"datasets.":[132],"implementation":[134],"made":[136],"public.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}