{"id":"https://openalex.org/W7154911856","doi":"https://doi.org/10.1016/j.array.2026.100817","title":"A hybrid approach for Bangla regional text classification using region-specific lexical oversampling and BERT ensemble learning","display_name":"A hybrid approach for Bangla regional text classification using region-specific lexical oversampling and BERT ensemble learning","publication_year":2026,"publication_date":"2026-04-19","ids":{"openalex":"https://openalex.org/W7154911856","doi":"https://doi.org/10.1016/j.array.2026.100817"},"language":"en","primary_location":{"id":"doi:10.1016/j.array.2026.100817","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.array.2026.100817","pdf_url":null,"source":{"id":"https://openalex.org/S4210194039","display_name":"Array","issn_l":"2590-0056","issn":["2590-0056"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Array","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1016/j.array.2026.100817","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072037880","display_name":"Babe Sultana","orcid":"https://orcid.org/0000-0001-9292-5868"},"institutions":[{"id":"https://openalex.org/I233772129","display_name":"Dhaka International University","ror":"https://ror.org/05nsh7a69","country_code":"BD","type":"education","lineage":["https://openalex.org/I233772129"]},{"id":"https://openalex.org/I2802576217","display_name":"Green University of Bangladesh","ror":"https://ror.org/04f7afq11","country_code":"BD","type":"education","lineage":["https://openalex.org/I2802576217"]},{"id":"https://openalex.org/I63169043","display_name":"United International University","ror":"https://ror.org/01tqv1p28","country_code":"BD","type":"education","lineage":["https://openalex.org/I63169043"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Babe Sultana","raw_affiliation_strings":["Computer Science and Engineering, Green University of Bangladesh, Kanchon 1460, Bangladesh","Computer Science and Engineering, United International University, Dhaka 1212, Bangladesh"],"raw_orcid":"https://orcid.org/0000-0001-9292-5868","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Green University of Bangladesh, Kanchon 1460, Bangladesh","institution_ids":["https://openalex.org/I2802576217"]},{"raw_affiliation_string":"Computer Science and Engineering, United International University, Dhaka 1212, Bangladesh","institution_ids":["https://openalex.org/I63169043","https://openalex.org/I233772129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133976873","display_name":"Ohidujjaman","orcid":"https://orcid.org/0000-0002-8776-7145"},"institutions":[{"id":"https://openalex.org/I233772129","display_name":"Dhaka International University","ror":"https://ror.org/05nsh7a69","country_code":"BD","type":"education","lineage":["https://openalex.org/I233772129"]},{"id":"https://openalex.org/I63169043","display_name":"United International University","ror":"https://ror.org/01tqv1p28","country_code":"BD","type":"education","lineage":["https://openalex.org/I63169043"]}],"countries":["BD"],"is_corresponding":true,"raw_author_name":"Ohidujjaman","raw_affiliation_strings":["Computer Science and Engineering, United International University, Dhaka 1212, Bangladesh"],"raw_orcid":"https://orcid.org/0000-0002-8776-7145","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, United International University, Dhaka 1212, Bangladesh","institution_ids":["https://openalex.org/I63169043","https://openalex.org/I233772129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014409376","display_name":"Suman Ahmmed","orcid":"https://orcid.org/0000-0002-9522-495X"},"institutions":[{"id":"https://openalex.org/I233772129","display_name":"Dhaka International University","ror":"https://ror.org/05nsh7a69","country_code":"BD","type":"education","lineage":["https://openalex.org/I233772129"]},{"id":"https://openalex.org/I63169043","display_name":"United International University","ror":"https://ror.org/01tqv1p28","country_code":"BD","type":"education","lineage":["https://openalex.org/I63169043"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Suman Ahmmed","raw_affiliation_strings":["Computer Science and Engineering, United International University, Dhaka 1212, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, United International University, Dhaka 1212, Bangladesh","institution_ids":["https://openalex.org/I63169043","https://openalex.org/I233772129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108542881","display_name":"MF Uddin","orcid":null},"institutions":[{"id":"https://openalex.org/I2802576217","display_name":"Green University of Bangladesh","ror":"https://ror.org/04f7afq11","country_code":"BD","type":"education","lineage":["https://openalex.org/I2802576217"]},{"id":"https://openalex.org/I46080048","display_name":"Jahangirnagar University","ror":"https://ror.org/04ywb0864","country_code":"BD","type":"education","lineage":["https://openalex.org/I46080048"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Mohammad Shorif Uddin","raw_affiliation_strings":["Computer Science and Engineering, Green University of Bangladesh, Kanchon 1460, Bangladesh","Computer Science and Engineering, Jahangirnagar University, Savar 1342, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Green University of Bangladesh, Kanchon 1460, Bangladesh","institution_ids":["https://openalex.org/I2802576217"]},{"raw_affiliation_string":"Computer Science and Engineering, Jahangirnagar University, Savar 1342, Bangladesh","institution_ids":["https://openalex.org/I46080048"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113997435","display_name":"Mohammad Nurul Huda","orcid":null},"institutions":[{"id":"https://openalex.org/I233772129","display_name":"Dhaka International University","ror":"https://ror.org/05nsh7a69","country_code":"BD","type":"education","lineage":["https://openalex.org/I233772129"]},{"id":"https://openalex.org/I63169043","display_name":"United International University","ror":"https://ror.org/01tqv1p28","country_code":"BD","type":"education","lineage":["https://openalex.org/I63169043"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Mohammad Nurul Huda","raw_affiliation_strings":["Computer Science and Engineering, United International University, Dhaka 1212, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, United International University, Dhaka 1212, Bangladesh","institution_ids":["https://openalex.org/I63169043","https://openalex.org/I233772129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5133976873"],"corresponding_institution_ids":["https://openalex.org/I233772129","https://openalex.org/I63169043"],"apc_list":{"value":1350,"currency":"USD","value_usd":1350},"apc_paid":{"value":1350,"currency":"USD","value_usd":1350},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.91891254,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"100817","last_page":"100817"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.19580000638961792,"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":0.19580000638961792,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.1826000064611435,"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":0.09359999746084213,"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/oversampling","display_name":"Oversampling","score":0.7598000168800354},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.5453000068664551},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5390999913215637},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5349000096321106},{"id":"https://openalex.org/keywords/bengali","display_name":"Bengali","score":0.5242000222206116},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.49959999322891235},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4343999922275543}],"concepts":[{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.7598000168800354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7459999918937683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6802999973297119},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.5453000068664551},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5390999913215637},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5349000096321106},{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.5242000222206116},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.49959999322891235},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49000000953674316},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4571000039577484},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4343999922275543},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2623000144958496}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.array.2026.100817","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.array.2026.100817","pdf_url":null,"source":{"id":"https://openalex.org/S4210194039","display_name":"Array","issn_l":"2590-0056","issn":["2590-0056"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Array","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.array.2026.100817","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.array.2026.100817","pdf_url":null,"source":{"id":"https://openalex.org/S4210194039","display_name":"Array","issn_l":"2590-0056","issn":["2590-0056"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Array","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.841854453086853,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2922081354","https://openalex.org/W3193668308","https://openalex.org/W3205434275","https://openalex.org/W3214933351","https://openalex.org/W4282030887","https://openalex.org/W4286354358","https://openalex.org/W4290714600","https://openalex.org/W4382401415","https://openalex.org/W4396790500","https://openalex.org/W4399202547","https://openalex.org/W4406097682","https://openalex.org/W4407245960"],"related_works":[],"abstract_inverted_index":{"Regional":[0],"text":[1,63],"analysis":[2],"reflects":[3],"the":[4,12,23,35,131,137,142,145,177,191,198,247],"lived":[5],"realities":[6],"of":[7,37,61,100,144,188,206,238,244],"diverse":[8],"communities":[9],"by":[10,69,114],"capturing":[11],"linguistic":[13],"richness":[14],"and":[15,29,56,73,92,111,152,156,163,184,209,233,240],"diversity":[16],"present":[17],"in":[18,49,123,133],"various":[19],"dialects.":[20],"It":[21],"bridges":[22],"gap":[24],"between":[25],"everyday":[26],"regional":[27,47,71],"usage":[28],"standardized":[30],"language":[31,38],"forms,":[32],"thereby":[33],"enhancing":[34],"inclusivity":[36],"technologies.":[39],"In":[40,136,172,190],"this":[41,173],"paper,":[42],"we":[43,140,194],"focus":[44,195],"on":[45,79,197,246],"five":[46,70],"dialects":[48],"Bangladesh,":[50],"namely":[51],"Chittagong,":[52],"Sylhet,":[53],"Noakhali,":[54],"Barishal,":[55],"Rangpur,":[57],"using":[58],"a":[59,87,124,185,203,221,241],"dataset":[60,66,132,147],"4218":[62],"samples.":[64],"The":[65,217],"is":[67,93,117,168,220],"validated":[68,113],"experts":[72],"categorized":[74],"into":[75],"three":[76,228],"tiers":[77],"based":[78],"an":[80,236],"assigned":[81],"agreement":[82],"criterion.":[83],"Tier":[84,150,153,164,199,248],"1":[85,165,200,249],"represents":[86],"strictly":[88],"filtered,":[89],"high-confidence":[90],"subset":[91],"used":[94,122,160,169],"primarily":[95],"for":[96,161,170],"evaluation.":[97],"A":[98],"set":[99],"region-specific":[101],"special":[102],"words,":[103],"which":[104],"belong":[105],"exclusively":[106,196],"to":[107,129,213],"their":[108,215],"respective":[109],"regions":[110],"are":[112,121,159],"domain":[115],"experts,":[116],"introduced.":[118],"These":[119],"words":[120],"linguistically":[125],"informed":[126],"oversampling":[127],"technique":[128,225],"balance":[130],"both":[134],"experiments.":[135],"first":[138],"experiment,":[139,193],"demonstrate":[141],"effectiveness":[143],"tiered":[146],"structure,":[148],"where":[149],"2":[151],"3":[154],"(medium-":[155],"low-confidence":[157],"subsets)":[158],"training,":[162],"(high-quality":[166],"subset)":[167],"testing.":[171],"setting,":[174],"BanglaBERT":[175],"achieves":[176],"best":[178],"individual":[179],"performance":[180],"with":[181],"67.45%":[182],"accuracy":[183,237],"weighted":[186,242],"F1-score":[187,243],"67.62%.":[189],"second":[192],"dataset,":[201],"applying":[202],"wide":[204],"range":[205],"machine":[207],"learning":[208,211],"deep":[210,223],"models":[212],"assess":[214],"effectiveness.":[216],"key":[218],"contribution":[219],"heterogeneous":[222],"ensemble":[224],"that":[226],"combines":[227],"BERT":[229],"models,":[230],"BanglaBERT,":[231],"BUETBERT,":[232],"DistilBERT,":[234],"achieving":[235],"85.17%":[239],"84.84%":[245],"dataset.":[250]},"counts_by_year":[],"updated_date":"2026-04-20T06:05:41.434183","created_date":"2026-04-20T00:00:00"}
