{"id":"https://openalex.org/W4402592623","doi":"https://doi.org/10.1109/access.2024.3463400","title":"The Applicability of LLMs in Generating Textual Samples for Analysis of Imbalanced Datasets","display_name":"The Applicability of LLMs in Generating Textual Samples for Analysis of Imbalanced Datasets","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402592623","doi":"https://doi.org/10.1109/access.2024.3463400"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3463400","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3463400","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":null,"license_id":null,"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.2024.3463400","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090372710","display_name":"Saroj Gopali","orcid":"https://orcid.org/0000-0003-3565-9756"},"institutions":[{"id":"https://openalex.org/I12315562","display_name":"Texas Tech University","ror":"https://ror.org/0405mnx93","country_code":"US","type":"education","lineage":["https://openalex.org/I12315562"]},{"id":"https://openalex.org/I33586118","display_name":"Lubbock Christian University","ror":"https://ror.org/02wb36b75","country_code":"US","type":"education","lineage":["https://openalex.org/I33586118"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saroj Gopali","raw_affiliation_strings":["Department of Computer Science, Texas Tech University, Lubbock, TX, USA","Department of Computer Science, Lubbock, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-3565-9756","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Texas Tech University, Lubbock, TX, USA","institution_ids":["https://openalex.org/I12315562"]},{"raw_affiliation_string":"Department of Computer Science, Lubbock, TX, USA","institution_ids":["https://openalex.org/I33586118"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083906665","display_name":"Faranak Abri","orcid":"https://orcid.org/0000-0003-3028-094X"},"institutions":[{"id":"https://openalex.org/I51504820","display_name":"San Jose State University","ror":"https://ror.org/04qyvz380","country_code":"US","type":"education","lineage":["https://openalex.org/I51504820"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Faranak Abri","raw_affiliation_strings":["Department of Computer Science, San Jose State University, San Jose, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-3028-094X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, San Jose State University, San Jose, CA, USA","institution_ids":["https://openalex.org/I51504820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026464816","display_name":"Akbar Siami Namin","orcid":"https://orcid.org/0000-0002-1646-7495"},"institutions":[{"id":"https://openalex.org/I12315562","display_name":"Texas Tech University","ror":"https://ror.org/0405mnx93","country_code":"US","type":"education","lineage":["https://openalex.org/I12315562"]},{"id":"https://openalex.org/I33586118","display_name":"Lubbock Christian University","ror":"https://ror.org/02wb36b75","country_code":"US","type":"education","lineage":["https://openalex.org/I33586118"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Akbar Siami Namin","raw_affiliation_strings":["Department of Computer Science, Texas Tech University, Lubbock, TX, USA","Department of Computer Science, Lubbock, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-1646-7495","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Texas Tech University, Lubbock, TX, USA","institution_ids":["https://openalex.org/I12315562"]},{"raw_affiliation_string":"Department of Computer Science, Lubbock, TX, USA","institution_ids":["https://openalex.org/I33586118"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102751548","display_name":"Keith S. Jones","orcid":"https://orcid.org/0000-0002-3463-0401"},"institutions":[{"id":"https://openalex.org/I12315562","display_name":"Texas Tech University","ror":"https://ror.org/0405mnx93","country_code":"US","type":"education","lineage":["https://openalex.org/I12315562"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keith S. Jones","raw_affiliation_strings":["Department of Psychological Sciences, Texas Tech University, Lubbock, TX, USA","Department of Psychological Sciences, Lubbock, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-3463-0401","affiliations":[{"raw_affiliation_string":"Department of Psychological Sciences, Texas Tech University, Lubbock, TX, USA","institution_ids":["https://openalex.org/I12315562"]},{"raw_affiliation_string":"Department of Psychological Sciences, Lubbock, TX, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.1383,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.89193446,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"12","issue":null,"first_page":"136451","last_page":"136465"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9768999814987183,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9768999814987183,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9768999814987183,"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":0.681859016418457},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32965344190597534},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3278973698616028},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32651281356811523},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3247862458229065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.681859016418457},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32965344190597534},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3278973698616028},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32651281356811523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3247862458229065}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2024.3463400","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3463400","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:scholarworks.sjsu.edu:faculty_rsca-6807","is_oa":true,"landing_page_url":"https://scholarworks.sjsu.edu/faculty_rsca/5808","pdf_url":null,"source":{"id":"https://openalex.org/S4377196389","display_name":"San Jos\u00e9 State University ScholarWorks (San Jose State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I51504820","host_organization_name":"San Jose State University","host_organization_lineage":["https://openalex.org/I51504820"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Research, Scholarly, and Creative Activity","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:610f1682ed3645579ac603c25d0d963e","is_oa":true,"landing_page_url":"https://doaj.org/article/610f1682ed3645579ac603c25d0d963e","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 12, Pp 136451-136465 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3463400","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3463400","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1672763025","display_name":null,"funder_award_id":"N00014-21-1-2007","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G3812703113","display_name":null,"funder_award_id":"2319803","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4440925640","display_name":null,"funder_award_id":"2319802","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1976766779","https://openalex.org/W1993220166","https://openalex.org/W1995875735","https://openalex.org/W2011301426","https://openalex.org/W2018329493","https://openalex.org/W2026449597","https://openalex.org/W2051039358","https://openalex.org/W2078706391","https://openalex.org/W2115973703","https://openalex.org/W2148143831","https://openalex.org/W2154868463","https://openalex.org/W2156163116","https://openalex.org/W2489098841","https://openalex.org/W2490662969","https://openalex.org/W2588115593","https://openalex.org/W2765811365","https://openalex.org/W2954996726","https://openalex.org/W2980748755","https://openalex.org/W3011686870","https://openalex.org/W3113304723","https://openalex.org/W3121453725","https://openalex.org/W3125937743","https://openalex.org/W3150635270","https://openalex.org/W3196248941","https://openalex.org/W4224930299","https://openalex.org/W4311415873","https://openalex.org/W4385245566","https://openalex.org/W4386025837","https://openalex.org/W4388650545","https://openalex.org/W4392703794","https://openalex.org/W4394603741","https://openalex.org/W6611681715","https://openalex.org/W6694517276","https://openalex.org/W6755207826","https://openalex.org/W6768817161"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0,24],"machine":[1],"learning":[2],"class":[3,99,169,178],"imbalance":[4,115,170],"is":[5,12],"a":[6],"pressing":[7],"issue,":[8],"where":[9],"the":[10,15,21,27,50,60,81,120,124,134,145,159,173,181],"model":[11,32],"biased":[13],"towards":[14],"majority":[16],"classes":[17],"and":[18,48,63,67,103,131,149,171],"underperforms":[19],"in":[20,42,114,133,166,176,180],"minority":[22,43,177],"classes.":[23,44],"textual":[25],"data,":[26],"natural":[28],"language":[29],"processing":[30],"(NLP)":[31],"bias":[33],"significantly":[34],"reduces":[35],"overall":[36],"accuracy,":[37],"along":[38],"with":[39,59,74,128,168],"poor":[40],"performance":[41,51],"This":[45],"paper":[46],"investigates":[47],"compares":[49],"of":[52,152],"transformer-based":[53],"models,":[54],"such":[55,83],"as":[56,84],"Multi-head":[57,129],"Attention":[58,130],"data":[61,76,94,107,112,126,161],"levels":[62,65],"algorithmic":[64],"approaches":[66],"BERT":[68,132],"(Bidirectional":[69],"Encoder":[70],"Representations":[71],"from":[72,119],"Transformers)":[73],"LLM-based":[75,125,160],"augmentation.":[77],"The":[78,117],"research":[79],"utilized":[80],"approaches,":[82],"Random":[85],"Over":[86],"Sampler,":[87],"Synthetic":[88],"Minority":[89],"Over-sampling":[90],"Technique":[91],"(SMOTE),":[92],"SMOTEENN,":[93],"augmentation":[95,108,127,162],"at":[96],"word":[97],"level,":[98],"weights,":[100],"L2":[101],"regularization":[102],"leveraging":[104],"GPT-3.5-Turbo\u2019s":[105],"for":[106],"to":[109],"create":[110],"additional":[111],"samples":[113],"dataset.":[116,183],"results":[118],"experiment":[121],"demonstrate":[122],"that":[123,158],"Myers-Briggs":[135],"Type":[136],"Indicator":[137],"(MBTI)":[138],"dataset":[139],"(a":[140],"highly":[141],"skewed":[142],"dataset)":[143],"achieves":[144],"highest":[146],"precision,":[147],"recall":[148],"F1":[150],"score":[151],"0.76":[153],"across":[154],"terms.":[155],"It":[156],"indicates":[157],"has":[163],"significant":[164],"improvements":[165],"dealing":[167],"improves":[172],"model\u2019s":[174],"accuracy":[175],"types":[179],"MBTI":[182]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}