{"id":"https://openalex.org/W4378418331","doi":"https://doi.org/10.18280/ria.370219","title":"BalBERT: A New Approach to Improving Dataset Balancing for Text Classification","display_name":"BalBERT: A New Approach to Improving Dataset Balancing for Text Classification","publication_year":2023,"publication_date":"2023-04-30","ids":{"openalex":"https://openalex.org/W4378418331","doi":"https://doi.org/10.18280/ria.370219"},"language":"en","primary_location":{"id":"doi:10.18280/ria.370219","doi":"https://doi.org/10.18280/ria.370219","is_oa":true,"landing_page_url":"https://doi.org/10.18280/ria.370219","pdf_url":"https://iieta.org/download/file/fid/98134","source":{"id":"https://openalex.org/S4210205895","display_name":"Revue d intelligence artificielle","issn_l":"0992-499X","issn":["0992-499X","1958-5748"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","norway-1","poland-20","russia-white-list-3"],"host_organization":"https://openalex.org/P4310312982","host_organization_name":"International Information and Engineering Technology Association","host_organization_lineage":["https://openalex.org/P4310312982"],"host_organization_lineage_names":["International Information and Engineering Technology Association"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Revue d'Intelligence Artificielle","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://iieta.org/download/file/fid/98134","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","observed_orcids":["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":["Department of Computer Science, University of MASCARA, Mascara 29000, Algeria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of MASCARA, Mascara 29000, Algeria","institution_ids":["https://openalex.org/I4210124230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046180299","display_name":"Mohammed Salem","orcid":"https://orcid.org/0000-0001-7052-5978","observed_orcids":["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":["Department of Computer Science, University of MASCARA, Mascara 29000, Algeria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of MASCARA, Mascara 29000, Algeria","institution_ids":["https://openalex.org/I4210124230"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5053292487"],"corresponding_institution_ids":["https://openalex.org/I4210124230"],"apc_list":null,"apc_paid":null,"fwci":0.4984,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.62173381,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"37","issue":"2","first_page":"425","last_page":"431"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.75,"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":0.75,"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":0.1168999969959259,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.07569999992847443,"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/text-classification","display_name":"text classification","score":0.7829999923706055},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.7730000019073486},{"id":"https://openalex.org/keywords/data-balancing","display_name":"data balancing","score":0.7850000262260437},{"id":"https://openalex.org/keywords/bert","display_name":"BERT","score":0.7850000262260437},{"id":"https://openalex.org/keywords/social-media-text","display_name":"social media text","score":0.7710000276565552}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6205064058303833},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3542949855327606},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3422655463218689},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33018261194229126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18280/ria.370219","doi":"https://doi.org/10.18280/ria.370219","is_oa":true,"landing_page_url":"https://doi.org/10.18280/ria.370219","pdf_url":"https://iieta.org/download/file/fid/98134","source":{"id":"https://openalex.org/S4210205895","display_name":"Revue d intelligence artificielle","issn_l":"0992-499X","issn":["0992-499X","1958-5748"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","norway-1","poland-20","russia-white-list-3"],"host_organization":"https://openalex.org/P4310312982","host_organization_name":"International Information and Engineering Technology Association","host_organization_lineage":["https://openalex.org/P4310312982"],"host_organization_lineage_names":["International Information and Engineering Technology Association"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Revue d'Intelligence Artificielle","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.18280/ria.370219","doi":"https://doi.org/10.18280/ria.370219","is_oa":true,"landing_page_url":"https://doi.org/10.18280/ria.370219","pdf_url":"https://iieta.org/download/file/fid/98134","source":{"id":"https://openalex.org/S4210205895","display_name":"Revue d intelligence artificielle","issn_l":"0992-499X","issn":["0992-499X","1958-5748"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","norway-1","poland-20","russia-white-list-3"],"host_organization":"https://openalex.org/P4310312982","host_organization_name":"International Information and Engineering Technology Association","host_organization_lineage":["https://openalex.org/P4310312982"],"host_organization_lineage_names":["International Information and Engineering Technology Association"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Revue d'Intelligence Artificielle","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4378418331.pdf","grobid_xml":"https://content.openalex.org/works/W4378418331.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1552146667","https://openalex.org/W1993626219","https://openalex.org/W2507698194","https://openalex.org/W2626778328","https://openalex.org/W2896457183","https://openalex.org/W2964822915","https://openalex.org/W3014153848","https://openalex.org/W3016608325","https://openalex.org/W3085804837","https://openalex.org/W3093607642","https://openalex.org/W3095319910","https://openalex.org/W3103646405","https://openalex.org/W3128179785","https://openalex.org/W3147773549","https://openalex.org/W3203150041","https://openalex.org/W4221020671","https://openalex.org/W4286436770","https://openalex.org/W4286449976","https://openalex.org/W4293027464","https://openalex.org/W4298343014","https://openalex.org/W4312491950","https://openalex.org/W4327795748"],"related_works":["https://openalex.org/W4327795748","https://openalex.org/W7204189264","https://openalex.org/W4206540574","https://openalex.org/W3103379492","https://openalex.org/W4285257926","https://openalex.org/W7212717893","https://openalex.org/W4388336509","https://openalex.org/W4411864770","https://openalex.org/W4383892345","https://openalex.org/W397701212"],"abstract_inverted_index":{"Text":[0],"classification":[1],"has":[2],"seen":[3],"a":[4,20,62,76],"lot":[5],"of":[6,22,96,108],"research,":[7],"especially":[8],"after":[9],"social":[10,44],"media":[11,45],"platforms":[12,46],"came":[13],"into":[14,19],"existence.It":[15],"involves":[16],"categorizing":[17],"text":[18,40,86],"variety":[21],"classes,":[23],"such":[24],"as":[25,110],"positive,":[26],"negative,":[27],"neutral,":[28],"or":[29],"any":[30],"other":[31],"class":[32],"label.The":[33],"primary":[34],"issue":[35,59],"is":[36,68,102],"that":[37,93],"the":[38,58,71,97,106,120,124],"usual":[39],"datasets":[41],"collected":[42],"from":[43],"are":[47],"skewed":[48],"(i.e.,":[49],"imbalanced).Consequently,":[50],"classifiers":[51],"become":[52],"less":[53],"effective.However,":[54],"this":[55],"paper":[56],"addresses":[57],"by":[60,112],"developing":[61],"new":[63,77,88],"technique":[64],"called":[65],"BalBERT,":[66],"which":[67,101],"based":[69],"on":[70],"BERT":[72,98,121],"scheme":[73],"and":[74,116,123],"includes":[75],"sublayer":[78,89],"to":[79],"improve":[80],"performance":[81],"when":[82],"dealing":[83],"with":[84],"imbalanced":[85],"classification.This":[87],"introduces":[90],"balancing":[91],"techniques":[92],"take":[94],"advantage":[95],"representation":[99],"step,":[100],"context-based.The":[103],"results":[104],"demonstrate":[105],"effectiveness":[107],"BalBERT":[109],"measured":[111],"two":[113],"metrics:":[114],"AVG-Recall":[115],"F1-score.It":[117],"outperforms":[118],"both":[119],"baseline":[122],"state-of-the-art":[125],"results.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-05-27T00:00:00"}