{"id":"https://openalex.org/W4414321996","doi":"https://doi.org/10.1109/access.2025.3611636","title":"LLM-Based Persona-Driven Text Data Augmentation","display_name":"LLM-Based Persona-Driven Text Data Augmentation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414321996","doi":"https://doi.org/10.1109/access.2025.3611636"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3611636","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3611636","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3611636","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031595119","display_name":"Hyeon Seong Jeong","orcid":null},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeon Seong Jeong","raw_affiliation_strings":["Graduate School of Metaverse, Sogang University, Seoul, South Korea","Graduate School of Metaverse, Sogang University, South Korea"],"raw_orcid":"https://orcid.org/0009-0000-0934-3913","affiliations":[{"raw_affiliation_string":"Graduate School of Metaverse, Sogang University, Seoul, South Korea","institution_ids":["https://openalex.org/I148751991"]},{"raw_affiliation_string":"Graduate School of Metaverse, Sogang University, South Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090381804","display_name":"Hankyeong Ko","orcid":"https://orcid.org/0009-0002-9382-8431"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Han Kyeong Ko","raw_affiliation_strings":["Graduate School of Metaverse, Sogang University, Seoul, South Korea","Graduate School of Metaverse, Sogang University, South Korea"],"raw_orcid":"https://orcid.org/0009-0002-9382-8431","affiliations":[{"raw_affiliation_string":"Graduate School of Metaverse, Sogang University, Seoul, South Korea","institution_ids":["https://openalex.org/I148751991"]},{"raw_affiliation_string":"Graduate School of Metaverse, Sogang University, South Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076950125","display_name":"Sooyong Park","orcid":"https://orcid.org/0000-0002-3979-0586"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soo Yong Park","raw_affiliation_strings":["Graduate School of Metaverse, Sogang University, Seoul, South Korea","Graduate School of Metaverse, Sogang University, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-3979-0586","affiliations":[{"raw_affiliation_string":"Graduate School of Metaverse, Sogang University, Seoul, South Korea","institution_ids":["https://openalex.org/I148751991"]},{"raw_affiliation_string":"Graduate School of Metaverse, Sogang University, South Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070488155","display_name":"Taehoon Kim","orcid":"https://orcid.org/0000-0003-4788-4651"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Taehoon Kim","raw_affiliation_strings":["Graduate School of Metaverse, Sogang University, Seoul, South Korea","Graduate School of Metaverse, Sogang University, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-4788-4651","affiliations":[{"raw_affiliation_string":"Graduate School of Metaverse, Sogang University, Seoul, South Korea","institution_ids":["https://openalex.org/I148751991"]},{"raw_affiliation_string":"Graduate School of Metaverse, Sogang University, South Korea","institution_ids":["https://openalex.org/I148751991"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148751991"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19254501,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"167560","last_page":"167577"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14074","display_name":"Persona Design and Applications","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T14074","display_name":"Persona Design and Applications","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/fluency","display_name":"Fluency","score":0.5561000108718872},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5314000248908997},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4650999903678894},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4625999927520752},{"id":"https://openalex.org/keywords/bigram","display_name":"Bigram","score":0.42649999260902405},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4018999934196472},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4009000062942505},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.39340001344680786},{"id":"https://openalex.org/keywords/pragmatics","display_name":"Pragmatics","score":0.38420000672340393}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8226000070571899},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6133999824523926},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5834000110626221},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.5561000108718872},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5314000248908997},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4650999903678894},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4625999927520752},{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.42649999260902405},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4018999934196472},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4009000062942505},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.39340001344680786},{"id":"https://openalex.org/C11693617","wikidata":"https://www.wikidata.org/wiki/Q181839","display_name":"Pragmatics","level":2,"score":0.38420000672340393},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3434000015258789},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C2781202465","wikidata":"https://www.wikidata.org/wiki/Q18346297","display_name":"Lexical diversity","level":3,"score":0.29269999265670776},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.28760001063346863},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2703999876976013},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.2685999870300293},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C95318506","wikidata":"https://www.wikidata.org/wiki/Q6588467","display_name":"Textual entailment","level":3,"score":0.2547999918460846},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3611636","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3611636","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:55aea01fba89496989df9cc01937cc88","is_oa":true,"landing_page_url":"https://doaj.org/article/55aea01fba89496989df9cc01937cc88","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 167560-167577 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3611636","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3611636","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2889326796","https://openalex.org/W2970988759","https://openalex.org/W3012064577","https://openalex.org/W3012253460","https://openalex.org/W3201915713","https://openalex.org/W4294214797","https://openalex.org/W4309028162","https://openalex.org/W4385571507","https://openalex.org/W4385893874","https://openalex.org/W4386025200","https://openalex.org/W4386097704","https://openalex.org/W4386858855","https://openalex.org/W4387212987","https://openalex.org/W4389519448","https://openalex.org/W4389524521","https://openalex.org/W4392692817","https://openalex.org/W4392943295","https://openalex.org/W4392981562","https://openalex.org/W4401580108","https://openalex.org/W4401980392","https://openalex.org/W4405528102","https://openalex.org/W4408413603"],"related_works":[],"abstract_inverted_index":{"Illicit":[0],"online":[1],"communication,":[2],"such":[3,43],"as":[4],"drug-dealing":[5,63],"dialogues,":[6],"is":[7],"increasingly":[8],"conducted":[9],"through":[10],"covert,":[11],"context":[12],"dependent":[13],"language":[14],"patterns":[15],"that":[16,87,95],"evade":[17],"traditional":[18,121],"detection":[19,29],"techniques":[20],"in":[21,42,145],"South":[22],"Korea.":[23],"However,":[24],"developing":[25],"reliable":[26],"AI":[27],"based":[28],"systems":[30],"remains":[31],"challenging":[32],"due":[33],"to":[34,59,154],"the":[35,78,96,128,134,140],"scarcity":[36],"of":[37,133,142],"real":[38],"world":[39],"training":[40],"data":[41,52,98],"sensitive":[44],"domains.":[45],"This":[46],"paper":[47],"proposes":[48],"a":[49],"novel":[50],"persona-driven":[51],"augmentation":[53,122,144],"framework":[54],"using":[55],"Large":[56],"Language":[57],"Model(LLM)":[58],"generate":[60],"realistic":[61],"synthetic":[62],"dialogues.":[64],"By":[65],"encoding":[66],"domain":[67],"specific":[68],"buyer":[69],"and":[70,83,113,116,131,149],"seller":[71],"personas":[72],"along":[73],"with":[74],"linguistic":[75],"behaviour":[76],"rules,":[77],"method":[79],"produces":[80],"contextually":[81],"coherent":[82],"semantically":[84],"diverse":[85],"dialogues":[86],"reflect":[88],"authentic":[89],"communication":[90],"styles.":[91],"Evaluation":[92],"results":[93],"demonstrate":[94],"augmented":[97],"preserves":[99],"key":[100],"stylistic":[101],"features":[102],"(high":[103],"cosine":[104],"similarity),":[105],"maintains":[106],"lexical":[107,117],"diversity":[108],"(TTR),":[109],"improves":[110],"fluency":[111],"(perplexity),":[112],"enhances":[114],"coherence":[115],"richness":[118],"(ROUGE-L),":[119],"outperforming":[120],"method.":[123],"Furthermore,":[124],"statistical":[125],"validation":[126],"confirms":[127],"semantic":[129],"consistency":[130],"stability":[132],"generated":[135],"data.":[136],"These":[137],"findings":[138],"highlight":[139],"viability":[141],"LLM-based":[143],"low-resource,":[146],"high-risk":[147],"domains":[148],"suggest":[150],"its":[151],"potential":[152],"transferability":[153],"other":[155],"specialized":[156],"NLP":[157],"applications":[158],"requiring":[159],"context-preserving":[160],"generation.":[161]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
