{"id":"https://openalex.org/W4413472805","doi":"https://doi.org/10.1177/01655515251362340","title":"Addressing class imbalance in text classification with LLMs: A prompt-based GPT-2 approach","display_name":"Addressing class imbalance in text classification with LLMs: A prompt-based GPT-2 approach","publication_year":2025,"publication_date":"2025-08-23","ids":{"openalex":"https://openalex.org/W4413472805","doi":"https://doi.org/10.1177/01655515251362340"},"language":"en","primary_location":{"id":"doi:10.1177/01655515251362340","is_oa":false,"landing_page_url":"https://doi.org/10.1177/01655515251362340","pdf_url":null,"source":{"id":"https://openalex.org/S68913162","display_name":"Journal of Information Science","issn_l":"0165-5515","issn":["0165-5515","1741-6485"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Science","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/A5053292487","display_name":"Laouni Mahmoudi","orcid":"https://orcid.org/0000-0001-6517-515X"},"institutions":[{"id":"https://openalex.org/I4210124230","display_name":"Universit\u00e9 Mustapha Stambouli de Mascara","ror":"https://ror.org/02vqddp65","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4210124230"]}],"countries":["DZ"],"is_corresponding":true,"raw_author_name":"Laouni Mahmoudi","raw_affiliation_strings":["LISYS Laboratory, University of Mascara, Algeria"],"raw_orcid":"https://orcid.org/0000-0001-6517-515X","affiliations":[{"raw_affiliation_string":"LISYS Laboratory, University of Mascara, Algeria","institution_ids":["https://openalex.org/I4210124230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046180299","display_name":"Mohammed Salem","orcid":"https://orcid.org/0000-0001-7052-5978"},"institutions":[{"id":"https://openalex.org/I4210124230","display_name":"Universit\u00e9 Mustapha Stambouli de Mascara","ror":"https://ror.org/02vqddp65","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4210124230"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"Mohammed Salem","raw_affiliation_strings":["LISYS Laboratory, University of Mascara, Algeria"],"raw_orcid":"https://orcid.org/0000-0001-7052-5978","affiliations":[{"raw_affiliation_string":"LISYS Laboratory, University of Mascara, Algeria","institution_ids":["https://openalex.org/I4210124230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085494668","display_name":"Nawaf Alharbe","orcid":"https://orcid.org/0000-0002-1900-420X"},"institutions":[{"id":"https://openalex.org/I120238654","display_name":"Saudi Electronic University","ror":"https://ror.org/05ndh7v49","country_code":"SA","type":"education","lineage":["https://openalex.org/I120238654"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Nawaf R Alharbe","raw_affiliation_strings":["Department of Computer Science, College of Computer Science and Engineering, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, College of Computer Science and Engineering, Saudi Arabia","institution_ids":["https://openalex.org/I120238654"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053292487"],"corresponding_institution_ids":["https://openalex.org/I4210124230"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10921264,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"52","issue":"3","first_page":"908","last_page":"922"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9993000030517578,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9993000030517578,"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/class","display_name":"Class (philosophy)","score":0.6183801293373108},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.43332424759864807},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3657758831977844},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.339011013507843},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.32135558128356934},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27536410093307495}],"concepts":[{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6183801293373108},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43332424759864807},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3657758831977844},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.339011013507843},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.32135558128356934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27536410093307495},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/01655515251362340","is_oa":false,"landing_page_url":"https://doi.org/10.1177/01655515251362340","pdf_url":null,"source":{"id":"https://openalex.org/S68913162","display_name":"Journal of Information Science","issn_l":"0165-5515","issn":["0165-5515","1741-6485"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Science","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W590132924","https://openalex.org/W1993626219","https://openalex.org/W2118978333","https://openalex.org/W2147376178","https://openalex.org/W2185967890","https://openalex.org/W2786025645","https://openalex.org/W2896457183","https://openalex.org/W3086905199","https://openalex.org/W4220893331","https://openalex.org/W4294927873","https://openalex.org/W4316469706","https://openalex.org/W4360584537","https://openalex.org/W4365512576","https://openalex.org/W4393312549"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0],"advent":[1],"of":[2,51,83,134,145],"Generative":[3],"Pre-trained":[4],"Transformer":[5],"(GPT)":[6],"has":[7,27],"significantly":[8],"impacted":[9],"various":[10],"downstream":[11,106,146],"natural":[12],"language":[13,22],"processing":[14],"(NLP)":[15],"tasks,":[16],"showcasing":[17],"its":[18],"remarkable":[19],"capabilities":[20,95],"in":[21,31,77],"understanding":[23],"and":[24,39,68,74,80,111,119],"generation.":[25],"It":[26],"demonstrated":[28],"state-of-the-art":[29,120],"performance":[30,114,144],"areas":[32],"such":[33],"as":[34],"machine":[35],"translation,":[36],"text":[37,108],"summarisation":[38],"question":[40],"answering.":[41],"In":[42,86],"this":[43],"study,":[44],"we":[45,88],"focus":[46],"on":[47,104],"addressing":[48],"the":[49,123,132,143],"issue":[50],"skewed":[52],"data":[53,138],"sets,":[54],"which":[55],"is":[56],"a":[57,105],"challenge":[58],"across":[59],"multiple":[60],"NLP":[61,147],"tasks.":[62,148],"Conventional":[63],"balancing":[64],"techniques":[65,118],"including":[66],"undersampling":[67],"oversampling":[69],"are":[70],"fraught":[71],"with":[72],"limitations":[73],"may":[75],"result":[76],"biased":[78],"predictions":[79],"insufficient":[81],"representation":[82],"minority":[84],"classes.":[85],"response,":[87],"propose":[89],"an":[90],"innovative":[91],"approach":[92,103],"harnessing":[93],"GPT\u2019s":[94],"to":[96,136],"generate":[97],"synthetic":[98],"samples.":[99],"We":[100],"evaluate":[101],"our":[102],"multi-class":[107],"classification":[109],"task":[110],"demonstrate":[112],"significant":[113],"improvements":[115],"over":[116],"conventional":[117],"methods,":[121],"surpassing":[122],"accuracy":[124],"by":[125],"more":[126],"than":[127],"10%.":[128],"These":[129],"findings":[130],"underscore":[131],"potential":[133],"GPT":[135],"revolutionise":[137],"set":[139],"balancing,":[140],"thereby":[141],"augmenting":[142]},"counts_by_year":[],"updated_date":"2026-06-07T06:13:29.825681","created_date":"2025-10-10T00:00:00"}