{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T12:06:53Z","timestamp":1777378013361,"version":"3.51.4"},"reference-count":28,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T00:00:00Z","timestamp":1775779200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Array"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.array.2026.100817","type":"journal-article","created":{"date-parts":[[2026,4,19]],"date-time":"2026-04-19T05:22:31Z","timestamp":1776576151000},"page":"100817","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A hybrid approach for Bangla regional text classification using region-specific lexical oversampling and BERT ensemble learning"],"prefix":"10.1016","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9292-5868","authenticated-orcid":false,"given":"Babe","family":"Sultana","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8776-7145","authenticated-orcid":false,"family":"Ohidujjaman","sequence":"additional","affiliation":[]},{"given":"Suman","family":"Ahmmed","sequence":"additional","affiliation":[]},{"given":"Mohammad Shorif","family":"Uddin","sequence":"additional","affiliation":[]},{"given":"Mohammad Nurul","family":"Huda","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.array.2026.100817_b1","first-page":"21","article-title":"Multi-class sentiment classification on Bengali social media comments using machine learning","volume":"4","author":"Haque","year":"2023","journal-title":"Int J Cogn Comput Eng"},{"key":"10.1016\/j.array.2026.100817_b2","series-title":"2023 26th International Conference on Computer and Information Technology","first-page":"1","article-title":"Bilingual spam sms detection using machine learning","author":"Sultana","year":"2023"},{"issue":"5","key":"10.1016\/j.array.2026.100817_b3","first-page":"475","article-title":"Comparative analysis of Bangla news classification: A study of fake news detection and multiclass classification using bert and fasttext","volume":"47","author":"Barua","year":"2025","journal-title":"Int J Comput Appl"},{"key":"10.1016\/j.array.2026.100817_b4","series-title":"2019 4th International Conference on Electrical Information and Communication Technology","first-page":"1","article-title":"Emotion detection from Bangla text corpus using naive bayes classifier","author":"Azmin","year":"2019"},{"key":"10.1016\/j.array.2026.100817_b5","doi-asserted-by":"crossref","first-page":"665","DOI":"10.7717\/peerj-cs.665","article-title":"Identifying vulgarity in Bengali social media textual content","volume":"7","author":"Sazzed","year":"2021","journal-title":"PeerJ Comput Sci"},{"issue":"11","key":"10.1016\/j.array.2026.100817_b6","doi-asserted-by":"crossref","first-page":"5463","DOI":"10.3390\/app12115463","article-title":"Multi\u2013label extreme learning machine (MLELMs) for Bangla regional speech recognition","volume":"12","author":"Hossain","year":"2022","journal-title":"Appl Sci"},{"key":"10.1016\/j.array.2026.100817_b7","series-title":"Vashantor: A large-scale multilingual benchmark dataset for automated translation of Bangla regional dialects to Bangla language","author":"Faria","year":"2023"},{"key":"10.1016\/j.array.2026.100817_b8","series-title":"Transcribing Bengali text with regional dialects to ipa using district guided tokens","author":"Islam","year":"2024"},{"key":"10.1016\/j.array.2026.100817_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.dib.2025.111276","article-title":"Onubad: A comprehensive dataset for automated conversion of Bangla regional dialects into standard Bengali dialect","volume":"58","author":"Sultana","year":"2025","journal-title":"Data Brief"},{"key":"10.1016\/j.array.2026.100817_b10","series-title":"BdRegionText: Bangladeshi regional dataset","author":"Sultana","year":"2024"},{"issue":"2","key":"10.1016\/j.array.2026.100817_b11","doi-asserted-by":"crossref","first-page":"414","DOI":"10.1016\/j.gltp.2021.08.039","article-title":"Sentimental analysis of Indian regional languages on social media","volume":"2","author":"Rakshitha","year":"2021","journal-title":"Glob Transit Proc"},{"key":"10.1016\/j.array.2026.100817_b12","doi-asserted-by":"crossref","first-page":"2886","DOI":"10.1016\/j.procs.2024.04.273","article-title":"Indo-Aryan dialect identification using deep learning ensemble model","volume":"235","author":"Subhash","year":"2024","journal-title":"Procedia Comput Sci"},{"issue":"8","key":"10.1016\/j.array.2026.100817_b13","first-page":"6","article-title":"Text classification for Marathi documents using supervised learning methods","volume":"155","author":"Bolaj","year":"2016","journal-title":"Int J Comput Appl"},{"issue":"6","key":"10.1016\/j.array.2026.100817_b14","doi-asserted-by":"crossref","first-page":"658","DOI":"10.1016\/j.jksuci.2019.03.007","article-title":"Text categorisation in quran and hadith: Overcoming the interre- lation challenges using machine learning and term weighting","volume":"33","author":"Rostam","year":"2021","journal-title":"J King Saud Univ-Comput Inf Sci"},{"key":"10.1016\/j.array.2026.100817_b15","series-title":"2021 International Conference on Advanced Computer Science and Information Systems","first-page":"1","article-title":"Multi-label classification for hate speech and abusive language in Indonesian-local languages","author":"Asti","year":"2021"},{"key":"10.1016\/j.array.2026.100817_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.sasc.2025.200203","article-title":"A systematic assessment of sentiment analysis models on Iraqi dialect-based texts","author":"Hussein","year":"2025","journal-title":"Syst Soft Comput"},{"key":"10.1016\/j.array.2026.100817_b17","series-title":"2024 IEEE 3rd conference on information technology and data science","first-page":"1","article-title":"A stacked ensemble model to identify Bangla religious hate comments","author":"Hasan","year":"2024"},{"key":"10.1016\/j.array.2026.100817_b18","series-title":"2024 27th International Conference on Computer and Information Technology","first-page":"1363","article-title":"An ensemble of machine learning models for classifying Bangla-English code-mixed sms as spam or ham","author":"Sultana","year":"2024"},{"key":"10.1016\/j.array.2026.100817_b19","series-title":"International Conference on Artificial Intelligence and Knowledge Processing","first-page":"252","article-title":"Abusive comment detection from Bengali\u2013 English code-mixed social media texts using ensemble of deep learning","author":"Fahim","year":"2024"},{"key":"10.1016\/j.array.2026.100817_b20","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.procs.2021.10.008","article-title":"An ensemble technique to classify multi-class textual emotion","volume":"193","author":"Parvin","year":"2021","journal-title":"Procedia Comput Sci"},{"key":"10.1016\/j.array.2026.100817_b21","series-title":"2024 International Conference on Advances in Computing, Communication, Electrical, and Smart Systems","first-page":"1","article-title":"Exploring transformer ensemble approach to classify cyberbullying text for the low-resource Bengali language","author":"Hoque","year":"2024"},{"issue":"02","key":"10.1016\/j.array.2026.100817_b22","doi-asserted-by":"crossref","first-page":"27","DOI":"10.38032\/jea.2024.02.001","article-title":"Depression intensity identification using transformer ensemble technique for the resource-constrained Bengali language","volume":"5","author":"Hoque","year":"2024","journal-title":"J Eng Adv"},{"issue":"02","key":"10.1016\/j.array.2026.100817_b23","doi-asserted-by":"crossref","first-page":"49","DOI":"10.38032\/jea.2023.02.003","article-title":"Detecting level of depression from social media posts for the low-resource Bengali language","volume":"4","author":"Hoque","year":"2023","journal-title":"J Eng Adv"},{"issue":"9","key":"10.1016\/j.array.2026.100817_b24","doi-asserted-by":"crossref","first-page":"36118","DOI":"10.2196\/36118","article-title":"Detection of depression severity using Bengali social media posts on mental health: study using natural language processing techniques","volume":"6","author":"Kabir","year":"2022","journal-title":"JMIR Form Res"},{"key":"10.1016\/j.array.2026.100817_b25","series-title":"BRWDS: A multipurpose dataset for Bangla Regional word detection","author":"Aiman","year":"2025"},{"key":"10.1016\/j.array.2026.100817_b26","doi-asserted-by":"crossref","first-page":"91855","DOI":"10.1109\/ACCESS.2022.3197662","article-title":"Bangla- bert: transformer-based efficient model for transfer learning and language understanding","volume":"10","author":"Kowsher","year":"2022","journal-title":"IEEE Access"},{"key":"10.1016\/j.array.2026.100817_b27","unstructured":"Sultana B, Hussain MG. BdRegionText: Resource Creation and Evaluation for Bangla Regional Text Classification with Machine Learning."},{"key":"10.1016\/j.array.2026.100817_b28","unstructured":"Wikipedia Contributors: Bengali dialects. Available at: https:\/\/en.wikipedia.org\/wiki\/Bengali_dialects. (Last Edited: 19 September 2025)."}],"container-title":["Array"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2590005626001402?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2590005626001402?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T09:09:48Z","timestamp":1777367388000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2590005626001402"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":28,"alternative-id":["S2590005626001402"],"URL":"https:\/\/doi.org\/10.1016\/j.array.2026.100817","relation":{},"ISSN":["2590-0056"],"issn-type":[{"value":"2590-0056","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A hybrid approach for Bangla regional text classification using region-specific lexical oversampling and BERT ensemble learning","name":"articletitle","label":"Article Title"},{"value":"Array","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.array.2026.100817","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"100817"}}