{"id":"https://openalex.org/W3157562165","doi":"https://doi.org/10.1109/tkde.2021.3076632","title":"Utility-Preserving Privacy Protection of Textual Documents via Word Embeddings","display_name":"Utility-Preserving Privacy Protection of Textual Documents via Word Embeddings","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3157562165","doi":"https://doi.org/10.1109/tkde.2021.3076632","mag":"3157562165"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2021.3076632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2021.3076632","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","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/A5110609598","display_name":"Fadi Hassan","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":false,"raw_author_name":"Fadi Hassan","raw_affiliation_strings":["Computer Engineering and Mathematics, Universitat Rovira i Virgili, Tarragona, Catalonia, Spain, (e-mail: fadi.hassan@urv.cat)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Engineering and Mathematics, Universitat Rovira i Virgili, Tarragona, Catalonia, Spain, (e-mail: fadi.hassan@urv.cat)","institution_ids":["https://openalex.org/I55952717"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043278211","display_name":"David S\u00e1nchez","orcid":"https://orcid.org/0000-0001-7275-7887"},"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":false,"raw_author_name":"David Sanchez","raw_affiliation_strings":["Computer Science and Mathematics, Universitat Rovira i Virgili, Tarragona, Catalonia, Spain, 43007 (e-mail: david.sanchez@urv.cat)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Mathematics, Universitat Rovira i Virgili, Tarragona, Catalonia, Spain, 43007 (e-mail: david.sanchez@urv.cat)","institution_ids":["https://openalex.org/I55952717"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051455237","display_name":"Josep Domingo\u2010Ferrer","orcid":"https://orcid.org/0000-0001-7213-4962"},"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":false,"raw_author_name":"Josep Domingo-Ferrer","raw_affiliation_strings":["Dept. of Computer Engineering and Maths, Univ. Rovira i Virgili, Tarragona, Catalonia, Spain, 43007 (e-mail: josep.domingo@urv.cat)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Engineering and Maths, Univ. Rovira i Virgili, Tarragona, Catalonia, Spain, 43007 (e-mail: josep.domingo@urv.cat)","institution_ids":["https://openalex.org/I55952717"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I55952717"],"apc_list":null,"apc_paid":null,"fwci":1.6378,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.8617651,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9997000098228455,"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":0.9997000098228455,"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/T10927","display_name":"Access Control and Trust","score":0.996399998664856,"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":0.9898999929428101,"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/computer-science","display_name":"Computer science","score":0.8919095993041992},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6464061737060547},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5843923091888428},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5799868702888489},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5657050609588623},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.5360223650932312},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5296164751052856},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5275822877883911},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.49460408091545105},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.4923635721206665},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4764804542064667},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4563295841217041},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.45409056544303894},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4454119801521301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.378031849861145},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.14302831888198853}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8919095993041992},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6464061737060547},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5843923091888428},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5799868702888489},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5657050609588623},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.5360223650932312},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5296164751052856},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5275822877883911},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.49460408091545105},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.4923635721206665},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4764804542064667},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4563295841217041},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.45409056544303894},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4454119801521301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.378031849861145},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14302831888198853},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2021.3076632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2021.3076632","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6499999761581421}],"awards":[{"id":"https://openalex.org/G5185571279","display_name":null,"funder_award_id":"308904","funder_id":"https://openalex.org/F4320323299","funder_display_name":"Norges Forskningsr\u00e5d"},{"id":"https://openalex.org/G7725498014","display_name":null,"funder_award_id":"2017 SGR 705","funder_id":"https://openalex.org/F4320321600","funder_display_name":"Departament d'Innovaci\u00f3, Universitats i Empresa, Generalitat de Catalunya"},{"id":"https://openalex.org/G7744117851","display_name":null,"funder_award_id":"H2020-871042","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8271342919","display_name":null,"funder_award_id":"H2020- 101006879","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/F4320321600","display_name":"Departament d'Innovaci\u00f3, Universitats i Empresa, Generalitat de Catalunya","ror":"https://ror.org/01bg62x04"},{"id":"https://openalex.org/F4320323299","display_name":"Norges Forskningsr\u00e5d","ror":"https://ror.org/00epmv149"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W113586804","https://openalex.org/W145956381","https://openalex.org/W1614298861","https://openalex.org/W1690606251","https://openalex.org/W1965063866","https://openalex.org/W1977246486","https://openalex.org/W1979796619","https://openalex.org/W2012309545","https://openalex.org/W2015620729","https://openalex.org/W2022166150","https://openalex.org/W2064202917","https://openalex.org/W2098917456","https://openalex.org/W2103528122","https://openalex.org/W2105646944","https://openalex.org/W2119067110","https://openalex.org/W2123442489","https://openalex.org/W2124090777","https://openalex.org/W2143603726","https://openalex.org/W2150259457","https://openalex.org/W2166656775","https://openalex.org/W2166956738","https://openalex.org/W2250539671","https://openalex.org/W2412696399","https://openalex.org/W2425617182","https://openalex.org/W2478460150","https://openalex.org/W2493916176","https://openalex.org/W2562898622","https://openalex.org/W2607951487","https://openalex.org/W2794140633","https://openalex.org/W2794598078","https://openalex.org/W2896457183","https://openalex.org/W2901147448","https://openalex.org/W2944797580","https://openalex.org/W2946558277","https://openalex.org/W2950225692","https://openalex.org/W2962739339","https://openalex.org/W2963879260","https://openalex.org/W2982673177","https://openalex.org/W3003815046","https://openalex.org/W3099236585","https://openalex.org/W3122816536","https://openalex.org/W4235505822","https://openalex.org/W4238700700","https://openalex.org/W4294170691","https://openalex.org/W4299488910","https://openalex.org/W4300536296","https://openalex.org/W6604617241","https://openalex.org/W6629028937","https://openalex.org/W6636510571","https://openalex.org/W6638773410","https://openalex.org/W6677712588","https://openalex.org/W6678768610","https://openalex.org/W6682691769","https://openalex.org/W6715454717","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W4386799044","https://openalex.org/W2773208253","https://openalex.org/W2560646951","https://openalex.org/W4297454206","https://openalex.org/W65104662","https://openalex.org/W1871748041","https://openalex.org/W2362286668","https://openalex.org/W2133382151","https://openalex.org/W2153339597","https://openalex.org/W4286432911"],"abstract_inverted_index":{"A":[0],"great":[1],"variety":[2],"of":[3,35,57,67,85,93,114,119,131,168],"mechanisms":[4],"have":[5],"been":[6,21],"proposed":[7],"to":[8,23,75,81,147,151],"protect":[9],"structured":[10],"databases":[11],"with":[12,175],"numerical":[13],"and":[14,37,88,108,189],"categorical":[15],"attributes;":[16],"however,":[17],"little":[18],"attention":[19],"has":[20],"devoted":[22],"unstructured":[24],"textual":[25,133],"data.":[26],"Textual":[27],"data":[28],"protection":[29,70,188],"requires":[30],"first":[31],"detecting":[32],"sensitive":[33,76],"pieces":[34,41],"text":[36],"then":[38],"masking":[39],"those":[40],"via":[42],"suppression":[43],"or":[44],"generalization.":[45],"Current":[46],"solutions":[47],"rely":[48],"on":[49,111,144,196],"classifiers":[50],"that":[51,125,181],"can":[52],"recognize":[53],"a":[54,82,105],"fixed":[55],"set":[56,84],"(allegedly":[58],"sensitive)":[59],"named":[60,197],"entities.":[61],"Yet,":[62],"such":[63],"approaches":[64],"fall":[65],"short":[66],"providing":[68],"adequate":[69],"because":[71],"in":[72,98],"reality":[73],"references":[74],"information":[77],"are":[78],"not":[79,89],"limited":[80],"predefined":[83],"entity":[86,95,146,198],"types,":[87],"all":[90],"the":[91,112,128,132,138,142,145,152,162,166,169],"appearances":[92],"certain":[94],"type":[96],"result":[97],"disclosure.":[99],"In":[100],"this":[101],"work":[102],"we":[103,122,136],"propose":[104],"more":[106,186],"general":[107],"flexible":[109],"based":[110,195],"notion":[113],"word":[115,120],"embedding.":[116],"By":[117],"means":[118],"embeddings":[121],"build":[123],"vectors":[124],"numerically":[126],"capture":[127],"semantic":[129],"relationships":[130],"terms.":[134],"Then":[135],"evaluate":[137],"disclosure":[139],"caused":[140],"by":[141,171],"terms":[143,174],"be":[148],"protected":[149],"according":[150],"similarity":[153],"between":[154],"their":[155],"vector":[156],"representations.":[157],"Our":[158],"method":[159],"also":[160],"preserves":[161],"semantics":[163],"(and,":[164],"therefore,":[165],"utility)":[167],"document":[170],"replacing":[172],"risky":[173],"privacy-preserving":[176],"generalizations.":[177],"Empirical":[178],"results":[179],"show":[180],"our":[182],"approach":[183],"offers":[184],"much":[185],"robust":[187],"greater":[190],"utility":[191],"preservation":[192],"than":[193],"methods":[194],"recognition.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}