{"id":"https://openalex.org/W7204465670","doi":"https://doi.org/10.21203/rs.3.rs-10437610/v1","title":"Class-Aware Semantic Hybrid Data Augmentation for Imbalanced Sentiment Classification Using Multiple Transformer Models","display_name":"Class-Aware Semantic Hybrid Data Augmentation for Imbalanced Sentiment Classification Using Multiple Transformer Models","publication_year":2026,"publication_date":"2026-08-27","ids":{"openalex":"https://openalex.org/W7204465670","doi":"https://doi.org/10.21203/rs.3.rs-10437610/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-10437610/v1","doi":"https://doi.org/10.21203/rs.3.rs-10437610/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-10437610/v1","pdf_url":"https://www.researchsquare.com/article/rs-10437610/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.researchsquare.com/article/rs-10437610/latest.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073028654","display_name":"Prashant Upadhyaya","orcid":"https://orcid.org/0000-0001-8266-5759","observed_orcids":["https://orcid.org/0000-0001-8266-5759"]},"institutions":[{"id":"https://openalex.org/I101407740","display_name":"Chandigarh University","ror":"https://ror.org/05t4pvx35","country_code":"IN","type":"education","lineage":["https://openalex.org/I101407740"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prashant Upadhyaya","raw_affiliation_strings":["Chandigarh University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chandigarh University","institution_ids":["https://openalex.org/I101407740"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006479709","display_name":"G. L. Saini","orcid":"https://orcid.org/0000-0003-4008-3309","observed_orcids":["https://orcid.org/0000-0003-4008-3309"]},"institutions":[{"id":"https://openalex.org/I73779912","display_name":"Manipal University Jaipur","ror":"https://ror.org/040h76494","country_code":"IN","type":"education","lineage":["https://openalex.org/I73779912"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"G.L. Saini","raw_affiliation_strings":["Manipal University Jaipur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Manipal University Jaipur","institution_ids":["https://openalex.org/I73779912"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049840770","display_name":"Atul Makrariya","orcid":"https://orcid.org/0000-0003-2460-1049","observed_orcids":["https://orcid.org/0000-0003-2460-1049"]},"institutions":[{"id":"https://openalex.org/I190570697","display_name":"Bundelkhand University","ror":"https://ror.org/0003ewr82","country_code":"IN","type":"education","lineage":["https://openalex.org/I190570697"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Atul Makrariya","raw_affiliation_strings":["Bundelkhand University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bundelkhand University","institution_ids":["https://openalex.org/I190570697"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006479709"],"corresponding_institution_ids":["https://openalex.org/I73779912"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9984999895095825,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9984999895095825,"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/T10028","display_name":"Topic Modeling","score":0.000699999975040555,"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":0.00039999998989515007,"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/minority-class-learning","display_name":"minority class learning","score":0.7799999713897705},{"id":"https://openalex.org/keywords/synonym-replacement","display_name":"synonym replacement","score":0.9800000190734863},{"id":"https://openalex.org/keywords/bert","display_name":"BERT","score":0.6919999718666077},{"id":"https://openalex.org/keywords/roberta","display_name":"RoBERTa","score":0.925000011920929},{"id":"https://openalex.org/keywords/distilbert","display_name":"DistilBERT","score":0.9919999837875366},{"id":"https://openalex.org/keywords/albert","display_name":"ALBERT","score":0.906000018119812}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7612000107765198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5554999709129333},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4749000072479248},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4706999957561493},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4472000002861023},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4433000087738037},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4106999933719635},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.3986999988555908},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3357999920845032},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C173483453","wikidata":"https://www.wikidata.org/wiki/Q1040689","display_name":"Synonym (taxonomy)","level":3,"score":0.29490000009536743},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2888999879360199},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C178009071","wikidata":"https://www.wikidata.org/wiki/Q93344","display_name":"Trigonometric functions","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-10437610/v1","doi":"https://doi.org/10.21203/rs.3.rs-10437610/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-10437610/v1","pdf_url":"https://www.researchsquare.com/article/rs-10437610/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-10437610/v1","doi":"https://doi.org/10.21203/rs.3.rs-10437610/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-10437610/v1","pdf_url":"https://www.researchsquare.com/article/rs-10437610/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204465670.pdf","grobid_xml":"https://content.openalex.org/works/W7204465670.grobid-xml"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W40549020","https://openalex.org/W2046858834","https://openalex.org/W2216973458","https://openalex.org/W2284660317","https://openalex.org/W2407776548","https://openalex.org/W2410415416","https://openalex.org/W2469565805","https://openalex.org/W2562607067","https://openalex.org/W2626778328","https://openalex.org/W2771841020","https://openalex.org/W2909652440","https://openalex.org/W2936044089","https://openalex.org/W2941002834","https://openalex.org/W2963341956","https://openalex.org/W2963921497","https://openalex.org/W2965373594","https://openalex.org/W2966614482","https://openalex.org/W2971296908","https://openalex.org/W2975059944","https://openalex.org/W2995261954","https://openalex.org/W2999286261","https://openalex.org/W3003618396","https://openalex.org/W3003775168","https://openalex.org/W3035056367","https://openalex.org/W3035269559","https://openalex.org/W3039918539","https://openalex.org/W3100754052","https://openalex.org/W3111700531","https://openalex.org/W3112027083","https://openalex.org/W3118860418","https://openalex.org/W3121883613","https://openalex.org/W3139061130","https://openalex.org/W3154265922","https://openalex.org/W3163321452","https://openalex.org/W3168867926","https://openalex.org/W3170251192","https://openalex.org/W3191586818","https://openalex.org/W3198002980","https://openalex.org/W3206401142","https://openalex.org/W3214618715","https://openalex.org/W3215822937","https://openalex.org/W4205184193","https://openalex.org/W4225487073","https://openalex.org/W4225983683","https://openalex.org/W4287891041","https://openalex.org/W4296341451","https://openalex.org/W4320801534","https://openalex.org/W4322718191","https://openalex.org/W4327656064","https://openalex.org/W4367280365","https://openalex.org/W4378189609","https://openalex.org/W4387247613","https://openalex.org/W4389776588","https://openalex.org/W4390885759","https://openalex.org/W4396508517","https://openalex.org/W4399040026","https://openalex.org/W4409180561","https://openalex.org/W4411347520","https://openalex.org/W4411718365","https://openalex.org/W4413393135","https://openalex.org/W7085778846"],"related_works":["https://openalex.org/W7127930518","https://openalex.org/W4417002992","https://openalex.org/W7204787841","https://openalex.org/W7160876484","https://openalex.org/W3159439818","https://openalex.org/W4404034825","https://openalex.org/W7166806887","https://openalex.org/W4413237800","https://openalex.org/W3199849862","https://openalex.org/W4414209938"],"abstract_inverted_index":{"Abstract":[0],"begin{abstract}Class":[1],"imbalance":[2,253],"remains":[3],"one":[4],"of":[5,25,36,108,269],"the":[6,34,106,134,163,167,180,200,226,236,246],"major":[7],"challenges":[8],"in":[9,61],"sentiment":[10,80,228,271],"classification":[11,272],"because":[12],"transformer-based":[13,154,270],"models":[14],"are":[15],"often":[16],"biased":[17],"toward":[18],"majority":[19],"classes,":[20,131],"leading":[21,262],"to":[22,188,195,207,214,263],"poor":[23],"recognition":[24],"minority":[26,130],"sentiments.":[27],"Although":[28],"existing":[29],"data":[30],"augmentation":[31,87,92],"techniques":[32],"increase":[33],"number":[35],"training":[37],"samples,":[38,57,110,261],"they":[39],"generally":[40],"apply":[41],"identical":[42],"transformations":[43],"across":[44,176],"all":[45],"classes":[46],"without":[47],"considering":[48],"class-specific":[49],"characteristics,":[50],"which":[51],"may":[52],"introduce":[53],"semantic":[54,111],"drift,":[55],"redundant":[56,123],"and":[58,101,152,166,192,258,266],"limited":[59],"improvements":[60,175,238],"minority-class":[62,222,260],"learning.To":[63],"address":[64],"these":[65],"limitations,":[66],"this":[67],"paper":[68],"proposes":[69],"a":[70],"Class-Aware":[71],"Semantic":[72],"Hybrid":[73],"Data":[74],"Augmentation":[75],"(CSHDA)":[76],"framework":[77,84,127,145,218,249],"for":[78,190,197,225],"imbalanced":[79],"classification.":[81],"The":[82,126,143,216],"proposed":[83,144,217,247],"combines":[85],"class-aware":[86],"probabilities":[88],"with":[89,160],"four":[90],"complementary":[91],"techniques,":[93],"namely":[94],"BERT-based":[95],"paraphrasing,":[96],"synonym":[97],"replacement,":[98],"random":[99,102],"insertion,":[100],"deletion.":[103],"To":[104],"ensure":[105],"quality":[107],"generated":[109],"consistency":[112],"is":[113],"validated":[114],"using":[115,148],"Sentence-BERT":[116],"cosine":[117],"similarity,":[118],"while":[119,139,209,230],"duplicate-aware":[120],"filtering":[121],"removes":[122],"augmented":[124],"instances.":[125],"augments":[128],"only":[129],"thereby":[132],"preserving":[133],"original":[135],"class":[136,252],"distribution":[137],"characteristics":[138],"reducing":[140],"learning":[141],"bias.":[142],"was":[146],"evaluated":[147],"BERT,":[149],"RoBERTa,":[150],"DistilBERT,":[151],"ALBERT":[153],"architectures":[155],"on":[156],"two":[157],"benchmark":[158],"datasets":[159],"different":[161],"characteristics:":[162],"CUFC":[164,181],"corpus":[165],"Twitter":[168,201],"Airline":[169],"dataset.":[170],"Experimental":[171],"results":[172,243],"demonstrate":[173,244],"consistent":[174,257],"both":[177],"datasets.":[178],"On":[179,199],"dataset,":[182,202],"Macro":[183],"F1-score":[184],"improved":[185,204,221,264],"from":[186,193,205,212],"60.80%":[187],"81.10%":[189],"BERT":[191,203],"55.43%":[194],"80.01%":[196],"DistilBERT.":[198],"60.65%":[206],"69.82%,":[208],"DistilBERT":[210],"increased":[211],"42.98%":[213],"71.21%.":[215],"also":[219],"substantially":[220],"recall,":[223],"particularly":[224],"neutral":[227],"class,":[229],"paired":[231],"statistical":[232],"analysis":[233],"confirmed":[234],"that":[235,245],"observed":[237],"were":[239],"statistically":[240],"significant.":[241],"These":[242],"CSHDA":[248],"effectively":[250],"mitigates":[251],"by":[254],"generating":[255],"semantically":[256],"diverse":[259],"robustness":[265],"cross-dataset":[267],"generalization":[268],"models.\\end{abstract}.":[273]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-08-28T00:00:00"}