{"id":"https://openalex.org/W7160872340","doi":"https://doi.org/10.1016/j.neunet.2026.109079","title":"Unsupervised utility evaluation of text anonymization methods via neural language models","display_name":"Unsupervised utility evaluation of text anonymization methods via neural language models","publication_year":2026,"publication_date":"2026-05-12","ids":{"openalex":"https://openalex.org/W7160872340","doi":"https://doi.org/10.1016/j.neunet.2026.109079","pmid":"https://pubmed.ncbi.nlm.nih.gov/42155273"},"language":"en","primary_location":{"id":"doi:10.1016/j.neunet.2026.109079","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neunet.2026.109079","pdf_url":null,"source":{"id":"https://openalex.org/S123019304","display_name":"Neural Networks","issn_l":"0893-6080","issn":["0893-6080","1879-2782"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Networks","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.neunet.2026.109079","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018217687","display_name":"Benet Manzanares-Salor","orcid":"https://orcid.org/0000-0001-7254-2560"},"institutions":[{"id":"https://openalex.org/I55952717","display_name":"Universitat Rovira i Virgili","ror":"https://ror.org/00g5sqv46","country_code":"ES","type":"education","lineage":["https://openalex.org/I55952717"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Benet Manzanares-Salor","raw_affiliation_strings":["Department of Computer Engineering and Mathematics, CYBERCAT-Center for Cybersecurity Research of Catalonia, ComSCIAM-Center for Computational Science and Applied Mathematics, Universitat Rovira i Virgili, Av. Paisos Catalans 26, Tarragona, 43007, Spain. Electronic address: benet.manzanares@urv.cat"],"raw_orcid":"https://orcid.org/0000-0001-7254-2560","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering and Mathematics, CYBERCAT-Center for Cybersecurity Research of Catalonia, ComSCIAM-Center for Computational Science and Applied Mathematics, Universitat Rovira i Virgili, Av. Paisos Catalans 26, Tarragona, 43007, Spain. Electronic address: benet.manzanares@urv.cat","institution_ids":["https://openalex.org/I55952717"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135861684","display_name":"David S\u00e1nchez","orcid":null},"institutions":[{"id":"https://openalex.org/I55952717","display_name":"Universitat Rovira i Virgili","ror":"https://ror.org/00g5sqv46","country_code":"ES","type":"education","lineage":["https://openalex.org/I55952717"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"David S\u00e1nchez","raw_affiliation_strings":["Department of Computer Engineering and Mathematics, CYBERCAT-Center for Cybersecurity Research of Catalonia, ComSCIAM-Center for Computational Science and Applied Mathematics, Universitat Rovira i Virgili, Av. Paisos Catalans 26, Tarragona, 43007, Spain. Electronic address: david.sanchez@urv.cat"],"raw_orcid":"https://orcid.org/0000-0001-7275-7887","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering and Mathematics, CYBERCAT-Center for Cybersecurity Research of Catalonia, ComSCIAM-Center for Computational Science and Applied Mathematics, Universitat Rovira i Virgili, Av. Paisos Catalans 26, Tarragona, 43007, Spain. Electronic address: david.sanchez@urv.cat","institution_ids":["https://openalex.org/I55952717"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008574874","display_name":"Pierre Lison","orcid":"https://orcid.org/0000-0002-7649-0689"},"institutions":[{"id":"https://openalex.org/I144648426","display_name":"Norwegian Computing Center","ror":"https://ror.org/02gm7te43","country_code":"NO","type":"nonprofit","lineage":["https://openalex.org/I144648426"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Pierre Lison","raw_affiliation_strings":["Norwegian Computing Center, Postboks 114 Blindern, Oslo, NO-0314, Norway. Electronic address: plison@nr.no"],"raw_orcid":"https://orcid.org/0000-0002-7649-0689","affiliations":[{"raw_affiliation_string":"Norwegian Computing Center, Postboks 114 Blindern, Oslo, NO-0314, Norway. Electronic address: plison@nr.no","institution_ids":["https://openalex.org/I144648426"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5008574874","https://openalex.org/A5018217687","https://openalex.org/A5135861684"],"corresponding_institution_ids":["https://openalex.org/I144648426","https://openalex.org/I55952717"],"apc_list":{"value":3350,"currency":"USD","value_usd":3350},"apc_paid":{"value":3350,"currency":"USD","value_usd":3350},"fwci":10.0442,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.98032787,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"202","issue":null,"first_page":"109079","last_page":"109079"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.39890000224113464,"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":0.39890000224113464,"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":0.2485000044107437,"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/T11719","display_name":"Data Quality and Management","score":0.043699998408555984,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4629000127315521},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36660000681877136},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3409999907016754},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.2777999937534332}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7950000166893005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6843000054359436},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4629000127315521},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4074000120162964},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39469999074935913},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36660000681877136},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2777999937534332},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2623000144958496}],"mesh":[{"descriptor_ui":"D000068240","descriptor_name":"Data Anonymization","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069558","descriptor_name":"Unsupervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018907","descriptor_name":"Privacy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1016/j.neunet.2026.109079","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neunet.2026.109079","pdf_url":null,"source":{"id":"https://openalex.org/S123019304","display_name":"Neural Networks","issn_l":"0893-6080","issn":["0893-6080","1879-2782"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Networks","raw_type":"journal-article"},{"id":"pmid:42155273","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42155273","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural networks : the official journal of the International Neural Network Society","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1016/j.neunet.2026.109079","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neunet.2026.109079","pdf_url":null,"source":{"id":"https://openalex.org/S123019304","display_name":"Neural Networks","issn_l":"0893-6080","issn":["0893-6080","1879-2782"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Networks","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315062","display_name":"Ministerio de Ciencia, Innovaci\u00f3n y Universidades","ror":null},{"id":"https://openalex.org/F4320323299","display_name":"Norges Forskningsr\u00e5d","ror":"https://ror.org/00epmv149"},{"id":"https://openalex.org/F4320336078","display_name":"Departament d'Empresa i Coneixement, Generalitat de Catalunya","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W992506503","https://openalex.org/W1690606251","https://openalex.org/W1965063866","https://openalex.org/W1987971958","https://openalex.org/W1995228216","https://openalex.org/W1995875735","https://openalex.org/W2006891577","https://openalex.org/W2015620729","https://openalex.org/W2020335020","https://openalex.org/W2059528803","https://openalex.org/W2064675550","https://openalex.org/W2065784179","https://openalex.org/W2105646944","https://openalex.org/W2133682331","https://openalex.org/W2159024459","https://openalex.org/W2161880183","https://openalex.org/W2170276412","https://openalex.org/W2562898622","https://openalex.org/W2621075239","https://openalex.org/W2794598078","https://openalex.org/W2891910613","https://openalex.org/W2896286428","https://openalex.org/W2941857399","https://openalex.org/W2949019015","https://openalex.org/W2963956191","https://openalex.org/W3195494141","https://openalex.org/W4221014796","https://openalex.org/W4234664880","https://openalex.org/W4292793781","https://openalex.org/W4366606855","https://openalex.org/W4382279449","https://openalex.org/W4402190773","https://openalex.org/W4406062884","https://openalex.org/W4406900157","https://openalex.org/W4410640334","https://openalex.org/W7160329411"],"related_works":[],"abstract_inverted_index":{"Text":[0],"anonymization":[1,208,226,248],"methods":[2,38],"strive":[3],"to":[4,18,110,126,173,206],"find":[5],"a":[6,61,95,212,220,240,244],"balance":[7],"between":[8],"privacy":[9,67,215],"protection":[10],"and":[11,53,88,124,146],"utility":[12,76,145,161,176,193],"preservation,":[13],"where":[14],"the":[15,19,22,50,64,73,114,136,140,158,175,191,195],"latter":[16],"refers":[17],"fact":[20],"that":[21,139,187,227],"anonymized":[23,164,196],"documents":[24],"are":[25,121],"still":[26],"analytically":[27],"useful":[28],"for":[29,63,84,163,224],"research":[30],"or":[31],"business":[32],"tasks.":[33],"The":[34],"performance":[35],"of":[36,66,75,194,243,246],"these":[37,79,151],"is":[39,58,70],"evaluated":[40],"empirically,":[41],"by":[42,179],"comparing":[43],"their":[44],"outputs":[45],"with":[46,211],"human-based":[47],"anonymizations":[48],"through":[49],"standard":[51],"precision":[52,69],"recall":[54,57],"metrics.":[55],"Whereas":[56],"used":[59,117],"as":[60,72,118],"proxy":[62],"level":[65],"attained,":[68],"interpreted":[71],"amount":[74],"preserved.":[77],"Nonetheless,":[78],"metrics":[80,130],"were":[81],"not":[82,229],"designed":[83],"evaluating":[85],"privacy-oriented":[86],"tasks":[87],"present":[89,157],"several":[90,103],"drawbacks.":[91],"First,":[92],"they":[93],"assume":[94],"unique":[96],"ground":[97,119],"truth":[98,120],"whereas,":[99],"in":[100,153],"text":[101,225,247],"anonymization,":[102],"masking":[104],"choices":[105],"can":[106],"be":[107],"equally":[108],"valid":[109],"prevent":[111],"re-identification.":[112],"Second,":[113],"human":[115,232],"annotations":[116],"inherently":[122],"subjective":[123],"prone":[125],"errors.":[127],"Third,":[128],"both":[129],"weight":[131],"terms":[132],"uniformly,":[133],"thereby":[134],"ignoring":[135],"varied":[137],"impact":[138],"terms'":[141],"semantics":[142],"have":[143],"on":[144,169,183],"re-identification":[147],"risk.":[148],"To":[149],"overcome":[150],"limitations,":[152],"this":[154,235],"paper":[155],"we":[156,237],"first":[159],"unsupervised":[160],"metric":[162,167,189],"texts.":[165],"Our":[166],"relies":[168],"neural":[170],"language":[171],"models":[172],"quantify":[174],"loss":[177],"incurred":[178],"anonymization.":[180],"Empirical":[181],"experiments":[182],"document":[184],"clustering":[185],"show":[186],"our":[188,217],"captures":[190],"actual":[192],"outcomes":[197],"more":[198,204],"accurately":[199],"than":[200],"precision,":[201],"while":[202],"being":[203],"sensitive":[205],"varying":[207],"intensities.":[209],"Together":[210],"previously":[213],"proposed":[214],"metric,":[216],"proposal":[218],"defines":[219],"complete":[221],"evaluation":[222,242],"framework":[223],"does":[228],"require":[230],"costly":[231],"annotations.":[233],"Using":[234],"framework,":[236],"also":[238],"report":[239],"comprehensive":[241],"variety":[245],"methods.":[249]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2026-05-12T00:00:00"}