{"id":"https://openalex.org/W4414393568","doi":"https://doi.org/10.32604/cmc.2025.068221","title":"A Study on Re-Identification of Natural Language Data Considering Korean Attributes","display_name":"A Study on Re-Identification of Natural Language Data Considering Korean Attributes","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414393568","doi":"https://doi.org/10.32604/cmc.2025.068221"},"language":"en","primary_location":{"id":"doi:10.32604/cmc.2025.068221","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.068221","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials & Continua","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.32604/cmc.2025.068221","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Segyeong Bang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Segyeong Bang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018871966","display_name":"Soeun Kim","orcid":"https://orcid.org/0000-0003-4172-6441"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soeun Kim","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119690278","display_name":"Gaeun Ahn","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gaeun Ahn","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Hyemin Hong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyemin Hong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5022052283","display_name":"Junhyoung Oh","orcid":"https://orcid.org/0000-0003-0783-852X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junhyoung Oh","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36539849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"85","issue":"3","first_page":"4629","last_page":"4643"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14409","display_name":"Educational Systems and Policies","score":0.7766000032424927,"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"}},"topics":[{"id":"https://openalex.org/T14409","display_name":"Educational Systems and Policies","score":0.7766000032424927,"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"}},{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.6920999884605408,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"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/T13751","display_name":"Diverse Approaches in Healthcare and Education Studies","score":0.6488000154495239,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/syllabic-verse","display_name":"Syllabic verse","score":0.5045999884605408},{"id":"https://openalex.org/keywords/authorship-attribution","display_name":"Authorship attribution","score":0.43619999289512634},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4131999909877777},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.39469999074935913},{"id":"https://openalex.org/keywords/linguistic-analysis","display_name":"Linguistic analysis","score":0.3885999917984009},{"id":"https://openalex.org/keywords/personally-identifiable-information","display_name":"Personally identifiable information","score":0.3882000148296356},{"id":"https://openalex.org/keywords/chatbot","display_name":"Chatbot","score":0.383899986743927},{"id":"https://openalex.org/keywords/mobile-phone","display_name":"Mobile phone","score":0.33160001039505005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7208999991416931},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6251999735832214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5932999849319458},{"id":"https://openalex.org/C194051139","wikidata":"https://www.wikidata.org/wiki/Q2629608","display_name":"Syllabic verse","level":2,"score":0.5045999884605408},{"id":"https://openalex.org/C3020202489","wikidata":"https://www.wikidata.org/wiki/Q2032038","display_name":"Authorship attribution","level":2,"score":0.43619999289512634},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4131999909877777},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.39469999074935913},{"id":"https://openalex.org/C2987219923","wikidata":"https://www.wikidata.org/wiki/Q777864","display_name":"Linguistic analysis","level":2,"score":0.3885999917984009},{"id":"https://openalex.org/C169093310","wikidata":"https://www.wikidata.org/wiki/Q3702971","display_name":"Personally identifiable information","level":2,"score":0.3882000148296356},{"id":"https://openalex.org/C2779041454","wikidata":"https://www.wikidata.org/wiki/Q870780","display_name":"Chatbot","level":2,"score":0.383899986743927},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.35440000891685486},{"id":"https://openalex.org/C2777421447","wikidata":"https://www.wikidata.org/wiki/Q17517","display_name":"Mobile phone","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26499998569488525},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.32604/cmc.2025.068221","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.068221","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials & Continua","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.32604/cmc.2025.068221","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.068221","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials & Continua","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2971087331","https://openalex.org/W3041140901","https://openalex.org/W3115690768","https://openalex.org/W3126935783","https://openalex.org/W3158596216","https://openalex.org/W3187216840","https://openalex.org/W3208563092","https://openalex.org/W4213420074","https://openalex.org/W4391774198","https://openalex.org/W4402768824","https://openalex.org/W4412889770","https://openalex.org/W4416034772"],"related_works":[],"abstract_inverted_index":{"This":[0,180],"study":[1],"analyzes":[2],"the":[3,21,56,102,162,173,182,194,210],"risks":[4],"of":[5,38,42,48,178,185,196,206,212],"re-identification":[6,133,197],"in":[7,51,189,215],"Korean":[8,98,114,186],"text":[9,99],"data":[10,18,29,67,200],"and":[11,72,80,120,123,146,158,160,168,201],"proposes":[12],"a":[13,152,204],"secure,":[14],"ethical":[15],"approach":[16],"to":[17,131],"anonymization.":[19],"Following":[20],"\u2018Lee":[22],"Luda\u2019":[23],"AI":[24,43],"chatbot":[25],"incident,":[26],"concerns":[27],"over":[28],"privacy":[30],"have":[31],"increased.":[32],"The":[33,191],"Personal":[34],"Information":[35],"Protection":[36],"Commission":[37],"Korea":[39],"conducted":[40],"inspections":[41],"services,":[44],"uncovering":[45],"850":[46],"cases":[47],"personal":[49,66,220],"information":[50],"user":[52],"input":[53],"datasets,":[54],"highlighting":[55],"need":[57],"for":[58,109,203],"pseudonymization":[59],"standards.":[60],"While":[61],"current":[62],"anonymization":[63,207,216],"techniques":[64],"remove":[65],"like":[68],"names,":[69],"phone":[70],"numbers,":[71],"addresses,":[73],"linguistic":[74,127,187,213],"features":[75,108,115,188],"such":[76],"as":[77],"writing":[78],"habits":[79],"language-specific":[81,107],"traits":[82,214],"can":[83],"still":[84],"identify":[85],"individuals":[86],"when":[87],"combined":[88,137],"with":[89],"other":[90],"data.":[91],"To":[92],"address":[93],"this,":[94],"we":[95,171],"analyzed":[96],"50,000":[97],"samples":[100],"from":[101],"X":[103],"platform,":[104],"focusing":[105],"on":[106],"authorship":[110,175],"attribution.":[111],"Unlike":[112],"English,":[113],"flexible":[116],"syntax,":[117],"honorifics,":[118],"syllabic":[119],"grapheme":[121],"patterns,":[122],"referential":[124],"terms.":[125],"These":[126],"characteristics":[128],"were":[129],"used":[130],"enhance":[132],"accuracy.":[134],"Our":[135],"experiments":[136],"five":[138],"machine":[139],"learning":[140],"models,":[141],"six":[142],"stopword":[143,169],"processing":[144],"methods,":[145,208],"four":[147],"morphological":[148,166],"analyzers.":[149],"By":[150],"using":[151],"tokenizer":[153],"that":[154],"captures":[155],"word":[156],"frequency":[157],"order,":[159],"employing":[161],"LSTM":[163],"model,":[164],"OKT":[165],"analyzer,":[167],"removal,":[170],"achieved":[172],"maximum":[174],"attributions":[176],"accuracy":[177],"90.51%.":[179],"demonstrates":[181],"significant":[183],"role":[184],"re-identification.":[190],"findings":[192],"emphasize":[193],"risk":[195],"through":[198],"language":[199],"call":[202],"re-evaluation":[205],"urging":[209],"consideration":[211],"beyond":[217],"simply":[218],"removing":[219],"information.":[221]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}