{"id":"https://openalex.org/W4409785640","doi":"https://doi.org/10.1007/s10489-026-07299-7","title":"Improving text classification on small-sized, imbalanced datasets with selective few-random-shot augmentation","display_name":"Improving text classification on small-sized, imbalanced datasets with selective few-random-shot augmentation","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W4409785640","doi":"https://doi.org/10.1007/s10489-026-07299-7"},"language":"en","primary_location":{"id":"doi:10.1007/s10489-026-07299-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10489-026-07299-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10489-026-07299-7.pdf","source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10489-026-07299-7.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022031796","display_name":"Lingshu Hu","orcid":"https://orcid.org/0000-0003-0304-882X"},"institutions":[{"id":"https://openalex.org/I184889055","display_name":"Washington and Lee University","ror":"https://ror.org/05r9xgf14","country_code":"US","type":"education","lineage":["https://openalex.org/I184889055"]},{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lingshu Hu","raw_affiliation_strings":["Department of Business Administration; Data Science Program, Washington and Lee University, Lexington, VA, 24450, USA","Department of Electrical Engineering & Computer Science, University of Missouri, Columbia, MO,  65211, USA"],"raw_orcid":"https://orcid.org/0000-0003-0304-882X","affiliations":[{"raw_affiliation_string":"Department of Business Administration; Data Science Program, Washington and Lee University, Lexington, VA, 24450, USA","institution_ids":["https://openalex.org/I184889055"]},{"raw_affiliation_string":"Department of Electrical Engineering & Computer Science, University of Missouri, Columbia, MO,  65211, USA","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007499225","display_name":"Peter Dolan","orcid":null},"institutions":[{"id":"https://openalex.org/I47251452","display_name":"Wake Forest University","ror":"https://ror.org/0207ad724","country_code":"US","type":"education","lineage":["https://openalex.org/I47251452"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Dolan","raw_affiliation_strings":["Department of Business Analytics, Wake Forest University, Winston-Salem, NC, 27109, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Business Analytics, Wake Forest University, Winston-Salem, NC, 27109, USA","institution_ids":["https://openalex.org/I47251452"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100334048","display_name":"Can Li","orcid":"https://orcid.org/0000-0002-3237-1477"},"institutions":[{"id":"https://openalex.org/I4210093996","display_name":"Dolby (United States)","ror":"https://ror.org/01eyenr26","country_code":"US","type":"company","lineage":["https://openalex.org/I4210093996"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Can Li","raw_affiliation_strings":["DoorDash, Inc, San Francisco, CA, 94107, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DoorDash, Inc, San Francisco, CA, 94107, USA","institution_ids":["https://openalex.org/I4210093996"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100350662","display_name":"Wenbo Wang","orcid":"https://orcid.org/0000-0001-8275-1067"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenbo Wang","raw_affiliation_strings":["Department of Electrical Engineering & Computer Science, University of Missouri, Columbia, MO,  65211, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering & Computer Science, University of Missouri, Columbia, MO,  65211, USA","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083442506","display_name":"Bin Pang","orcid":"https://orcid.org/0000-0003-0362-4700"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin Pang","raw_affiliation_strings":["Department of Electrical Engineering & Computer Science, University of Missouri, Columbia, MO,  65211, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering & Computer Science, University of Missouri, Columbia, MO,  65211, USA","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057883374","display_name":"Yi Shang","orcid":"https://orcid.org/0000-0001-7771-4034"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yi Shang","raw_affiliation_strings":["Department of Electrical Engineering & Computer Science, University of Missouri, Columbia, MO,  65211, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering & Computer Science, University of Missouri, Columbia, MO,  65211, USA","institution_ids":["https://openalex.org/I76835614"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5022031796","https://openalex.org/A5057883374"],"corresponding_institution_ids":["https://openalex.org/I184889055","https://openalex.org/I76835614"],"apc_list":{"value":3190,"currency":"USD","value_usd":3190},"apc_paid":{"value":3190,"currency":"USD","value_usd":3190},"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.00834299,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"56","issue":"9","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9991999864578247,"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":0.9991999864578247,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9990000128746033,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9962999820709229,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6704822778701782},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5625525116920471},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5363792777061462},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5089163780212402},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4743815064430237},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.41326141357421875},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3312954902648926},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.11118704080581665},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10405939817428589}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6704822778701782},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5625525116920471},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5363792777061462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5089163780212402},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4743815064430237},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.41326141357421875},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3312954902648926},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.11118704080581665},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10405939817428589},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10489-026-07299-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10489-026-07299-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10489-026-07299-7.pdf","source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-article"},{"id":"doi:10.2139/ssrn.5230886","is_oa":true,"landing_page_url":"https://doi.org/10.2139/ssrn.5230886","pdf_url":null,"source":{"id":"https://openalex.org/S4210172589","display_name":"SSRN Electronic Journal","issn_l":"1556-5068","issn":["1556-5068"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1318003438","host_organization_name":"RELX Group (Netherlands)","host_organization_lineage":["https://openalex.org/I1318003438"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.1007/s10489-026-07299-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10489-026-07299-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10489-026-07299-7.pdf","source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6700000166893005}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320311887","display_name":"Washington and Lee University","ror":"https://ror.org/05r9xgf14"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409785640.pdf","grobid_xml":"https://content.openalex.org/works/W4409785640.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1563938718","https://openalex.org/W1614298861","https://openalex.org/W2081580037","https://openalex.org/W2103614420","https://openalex.org/W2153579005","https://openalex.org/W2170240176","https://openalex.org/W2338318698","https://openalex.org/W2472223596","https://openalex.org/W2561529111","https://openalex.org/W2766022138","https://openalex.org/W2800788706","https://openalex.org/W2836242602","https://openalex.org/W2896457183","https://openalex.org/W2905266130","https://openalex.org/W2908694192","https://openalex.org/W2953484861","https://openalex.org/W2961125888","https://openalex.org/W2963545917","https://openalex.org/W2971296908","https://openalex.org/W2979826702","https://openalex.org/W2980748755","https://openalex.org/W2986191653","https://openalex.org/W3014673391","https://openalex.org/W3081972231","https://openalex.org/W3188875708","https://openalex.org/W4206555648","https://openalex.org/W4206590831","https://openalex.org/W4210376758","https://openalex.org/W4220718358","https://openalex.org/W4225269968","https://openalex.org/W4294170691","https://openalex.org/W4319866297","https://openalex.org/W4324118148","https://openalex.org/W4324344187","https://openalex.org/W4327747614","https://openalex.org/W4386245246","https://openalex.org/W4386621171","https://openalex.org/W7019159621"],"related_works":["https://openalex.org/W2497720472","https://openalex.org/W4292659306","https://openalex.org/W3044321615","https://openalex.org/W2806221744","https://openalex.org/W2326937258","https://openalex.org/W394267150","https://openalex.org/W2773965352","https://openalex.org/W4294892107","https://openalex.org/W2357748469","https://openalex.org/W2392917037"],"abstract_inverted_index":{"Abstract":[0],"Small":[1],"and":[2,69,83,96,113,115,120,132,171],"highly":[3],"imbalanced":[4,43,184],"text":[5,44,129],"datasets":[6,106],"often":[7],"produce":[8],"brittle":[9],"classifiers":[10],"because":[11],"scarce":[12],"minority":[13,67,161],"examples":[14,68],"provide":[15],"limited":[16],"coverage":[17],"of":[18,110,118],"class":[19,23],"semantics,":[20],"while":[21,163],"skewed":[22],"distributions":[24],"bias":[25],"decision":[26],"boundaries":[27],"toward":[28],"the":[29,62,138,143,151],"majority":[30],"class.":[31],"We":[32],"propose":[33],"Selective":[34],"Few-Random-Shot":[35],"Augmentation":[36],"(SFRSA),":[37],"a":[38,57,97],"generate-then-select":[39],"framework":[40],"for":[41],"low-resource":[42],"classification.":[45],"SFRSA":[46,122,159],"first":[47],"over-generates":[48],"minority-class":[49],"candidates":[50],"through":[51],"few-random-shot":[52],"LLM":[53],"prompting,":[54],"then":[55],"selects":[56],"fixed-budget":[58],"subset":[59],"by":[60],"optimizing":[61],"trade-off":[63],"between":[64],"relevance":[65],"to":[66,154,179],"diversity":[70],"among":[71],"selected":[72],"samples":[73],"in":[74,142,182],"embedding":[75],"space.":[76],"To":[77],"operationalize":[78],"this":[79],"idea,":[80],"we":[81],"develop":[82],"compare":[84],"three":[85,104],"selection":[86,152],"modules:":[87],"centroid-guided":[88],"clustering":[89],"(CGC),":[90],"determinantal":[91],"point":[92],"process":[93],"(DPP)":[94],"selection,":[95],"training-aware":[98],"influence-utility":[99],"DPP":[100],"(IU-DPP)":[101],"variant.":[102],"Across":[103],"benchmark":[105],"under":[107],"training":[108],"sizes":[109],"500,":[111],"1000,":[112],"2000":[114],"imbalance":[116],"ratios":[117],"4:1":[119],"9:1,":[121],"consistently":[123],"improves":[124],"minority-sensitive":[125],"performance":[126],"over":[127],"classic":[128],"augmentation":[130],"methods":[131],"standard":[133],"LLM-based":[134],"generation":[135],"baselines,":[136],"with":[137],"largest":[139],"gains":[140],"appearing":[141],"most":[144],"data-scarce":[145],"settings.":[146,185],"A":[147],"similarity\u2013diversity":[148],"analysis":[149],"links":[150],"objective":[153],"downstream":[155],"gains,":[156],"showing":[157],"that":[158],"preserves":[160],"semantics":[162],"avoiding":[164],"near-duplicate":[165],"generations.":[166],"The":[167],"method":[168],"is":[169],"model-agnostic":[170],"can":[172],"be":[173],"integrated":[174],"into":[175],"existing":[176],"NLP":[177],"pipelines":[178],"improve":[180],"classification":[181],"low-resource,":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2025-10-10T00:00:00"}