{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T22:13:40Z","timestamp":1791843220731,"version":"4.3.4"},"reference-count":35,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T00:00:00Z","timestamp":1749427200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002383","name":"King Saud University","doi-asserted-by":"publisher","award":["RSPD2024R951"],"award-info":[{"award-number":["RSPD2024R951"]}],"id":[{"id":"10.13039\/501100002383","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Bangla news floods the web, and the need for smarter and more efficient classification techniques is greater than ever. Previous studies mostly focused on traditional models, overlooking the potential of hybrid techniques to handle the ever-growing complex dataset and its linguistic patterns in Bangla to achieve higher accuracy. Addressing the challenge, this study presents a comprehensive approach to classify Bangla news articles into eight distinct categories using various machine learning and deep learning techniques. The use of traditional machine learning algorithms, deep learning architectures, and hybrid models, including novel stacking classifiers, was a part of our experiment. This study utilized a dataset of 118,404 Bangla news articles, applying rigorous feature extraction techniques including TF-IDF vectorization and word2Vec embeddings. Our best-performing model, a stacking meta-classifier combining bidirectional long short-term memory and support vector machine, achieved a remarkable 94% accuracy, leaving all basic models\u2019 performance behind. Also, we provided an in-depth analysis of model performances, including confusion matrices, ROC curves, and error analysis, offering insights into the strengths and limitations of each approach. This research contributes significantly to the field of Bangla natural language processing and demonstrates the efficacy of ensemble methods and deep learning in news classification for low-resource languages.<\/jats:p>","DOI":"10.1371\/journal.pone.0321291","type":"journal-article","created":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T17:27:36Z","timestamp":1749490056000},"page":"e0321291","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":12,"title":["BanglaNewsClassifier: A machine learning approach for news classification in Bangla Newspapers using hybrid stacking classifiers"],"prefix":"10.1371","volume":"20","author":[{"given":"Tanzir","family":"Hossain","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ar-Rafi","family":"Islam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5759-022X","authenticated-orcid":true,"given":"Md Humaion Kabir","family":"Mehedi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0198-3734","authenticated-orcid":true,"given":"Annajiat Alim","family":"Rasel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"M.","family":"Abdullah-AL-Wadud","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3403-4095","authenticated-orcid":true,"given":"Jia","family":"Uddin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,6,9]]},"reference":[{"issue":"4","key":"pone.0321291.ref001","first-page":"77","article-title":"Topic modelling in Bangla language: an LDA approach to optimize topics and news classification","volume":"11","author":"M Mouhoub","year":"2018","journal-title":"Comput Inf Sci"},{"key":"pone.0321291.ref002","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"L Ouyang","year":"2022","journal-title":"Adv Neural Inf Process Syst"},{"key":"pone.0321291.ref003","article-title":"Bag of tricks for efficient text classification","author":"A Joulin","year":"2016","journal-title":"arXiv Preprint"},{"issue":"9","key":"pone.0321291.ref004","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3560815","article-title":"Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing","volume":"55","author":"P Liu","year":"2023","journal-title":"ACM Comput Surv"},{"issue":"4","key":"pone.0321291.ref005","doi-asserted-by":"crossref","first-page":"150","DOI":"10.3390\/info10040150","article-title":"Text classification algorithms: a survey","volume":"10","author":"K Kowsari","year":"2019","journal-title":"Information"},{"key":"pone.0321291.ref006","article-title":"Pre-training of deep bidirectional transformers for language understanding","author":"J Devlin","year":"2018","journal-title":"arXiv Preprint"},{"key":"pone.0321291.ref007","doi-asserted-by":"crossref","first-page":"8440","DOI":"10.18653\/v1\/2020.acl-main.747","article-title":"Unsupervised cross-lingual representation learning at scale.","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"A Conneau","year":"2020"},{"key":"pone.0321291.ref008","doi-asserted-by":"crossref","unstructured":"Islam R, Hasan M, Rashid M, Khatun R. Bangla to English translation using sequence to sequence learning model based recurrent neural networks. In: International Conference on Machine Intelligence and Emerging Technologies. Springer; 2022. p. 458\u201367.","DOI":"10.1007\/978-3-031-34619-4_36"},{"key":"pone.0321291.ref009","doi-asserted-by":"crossref","first-page":"45194","DOI":"10.1109\/ACCESS.2023.3267746","article-title":"B-NER: a novel Bangla named entity recognition dataset with largest entities and its baseline evaluation","volume":"11","author":"MZ Haque","year":"2023","journal-title":"IEEE Access"},{"key":"pone.0321291.ref010","doi-asserted-by":"crossref","unstructured":"Sharif O, Hoque MM, Hossain E. Sentiment analysis of Bengali texts on online restaurant reviews using multinomial Na\u0308\u0131ve Bayes. In: 2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT). IEEE; 2019. p. 1\u20136.","DOI":"10.1109\/ICASERT.2019.8934655"},{"issue":"1","key":"pone.0321291.ref011","first-page":"1","article-title":"Accurate prediction of bangla text article categorization by utilizing novel bangla stemmer","volume":"14","author":"M Uddin","year":"2024","journal-title":"Int J Automat Smart Technol"},{"issue":"3","key":"pone.0321291.ref012","doi-asserted-by":"crossref","first-page":"584","DOI":"10.12928\/telkomnika.v21i3.23416","article-title":"Comparison analysis of Bangla news articles classification using support vector machine and logistic regression","volume":"21","author":"MG Hussain","year":"2023","journal-title":"Telkomnika"},{"key":"pone.0321291.ref013","article-title":"Media bias matters: understanding the impact of politically biased news on vaccine attitudes in social media","author":"B Jiang","year":"2024","journal-title":"arXiv Preprint"},{"key":"pone.0321291.ref014","doi-asserted-by":"crossref","unstructured":"Dufraisse E, Popescu A, Tourille J, Brun A, Deshayes J. MAD-TSC: a multilingual aligned news dataset for target-dependent sentiment classification. In: 61st Annual Meeting of the Association for Computational Linguistics; 2023.","DOI":"10.18653\/v1\/2023.acl-long.461"},{"key":"pone.0321291.ref015","doi-asserted-by":"crossref","unstructured":"Al-Qarqaz A, Abdullah M. Team justr00 at semeval-2023 task 3: transformers for news articles classification. In: Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023); 2023. p. 1213\u20136.","DOI":"10.18653\/v1\/2023.semeval-1.168"},{"key":"pone.0321291.ref016","doi-asserted-by":"crossref","unstructured":"Alami H, Benlahbib A, El Mahdaouy A, Berrada I. Um6p at SemEval-2023 Task 3: news genre classification based on transformers, graph convolution networks and number of sentences. In: Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023); 2023. p. 856\u201361.","DOI":"10.18653\/v1\/2023.semeval-1.118"},{"key":"pone.0321291.ref017","doi-asserted-by":"crossref","unstructured":"Billert F, Conrad S. Hhu at semeval-2023 task 3: an adapter-based approach for news genre classification. In: Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023); 2023. p. 1166\u201371.","DOI":"10.18653\/v1\/2023.semeval-1.162"},{"key":"pone.0321291.ref018","doi-asserted-by":"crossref","unstructured":"Devatine N, Muller P, Braud C. Melodi at semeval-2023 task 3: In-domain pre-training for low-resource classification of news articles. In: Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023); 2023. p. 108\u201313.","DOI":"10.18653\/v1\/2023.semeval-1.14"},{"key":"pone.0321291.ref019","doi-asserted-by":"crossref","unstructured":"Mittal S, Magdum V, Hiwarkhedkar S, Dhekane O, Joshi R. L3Cube-MahaNews: news-based short text and long document classification datasets in Marathi. In: International Conference on Speech and Language Technologies for low-resource Languages; Springer; 2023. p. 52\u201363.","DOI":"10.1007\/978-3-031-58495-4_4"},{"key":"pone.0321291.ref020","article-title":"When LLMs are unfit use FastFit: fast and effective text classification with many classes","author":"A Yehudai","year":"2024","journal-title":"arXiv Preprint"},{"key":"pone.0321291.ref021","unstructured":"Bade G, Kolesnikova O, Sidorov G, Oropeza J. Social media fake news classification using machine learning algorithm. In: Proceedings of the Fourth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages; 2024. p. 24\u20139."},{"key":"pone.0321291.ref022","unstructured":"3237407117188Rahman T, Raihan A, Rahman M, Hossain J, Ahsan S, Das A, et al. CUET DUO@ DravidianLangTech EACL2024: fake news classification using Malayalam-BERT. In: Proceedings of the Fourth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages; 2024. p. 223\u20138."},{"key":"pone.0321291.ref023","doi-asserted-by":"crossref","first-page":"44462","DOI":"10.1109\/ACCESS.2024.3381038","article-title":"Advancing fake news detection: hybrid deep learning with FastText and explainable AI","volume":"12","author":"E Hashmi","year":"2024","journal-title":"IEEE Access"},{"key":"pone.0321291.ref024","doi-asserted-by":"crossref","unstructured":"Murindanyi S, Yiiki BA, Katumba A, Nakatumba-Nabende J. Explainable machine learning models for Swahili News classification. In: Proceedings of the 2023 7th International Conference on Natural Language Processing and Information Retrieval. 2023. p. 12\u201318. doi: 10.1145\/3639233.3639250","DOI":"10.1145\/3639233.3639250"},{"issue":"3","key":"pone.0321291.ref025","doi-asserted-by":"crossref","first-page":"584","DOI":"10.12928\/telkomnika.v21i3.23416","article-title":"Comparison analysis of bangla news articles classification using support vector machine and logistic regression","volume":"21","author":"MG Hussain","year":"2023","journal-title":"Telkomnika (Telecommun Comput Electron Control)"},{"key":"pone.0321291.ref026","doi-asserted-by":"crossref","DOI":"10.7717\/peerj-cs.677","article-title":"Topic2features: a novel framework to classify noisy and sparse textual data using LDA topic distributions","volume":"7","author":"JA Wahid","year":"2021","journal-title":"PeerJ Comput Sci"},{"issue":"2","key":"pone.0321291.ref027","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1007\/s11634-023-00536-8","article-title":"Threshold-based Na\u00efve Bayes classifier","volume":"18","author":"M Romano","year":"2024","journal-title":"Adv Data Anal Classif"},{"issue":"1","key":"pone.0321291.ref028","first-page":"67","article-title":"Sentiment analysis using support vector machine and random forest","volume":"3","author":"TA Khan","year":"2024","journal-title":"J Inf Web Eng"},{"key":"pone.0321291.ref029","article-title":"Learning a decision tree algorithm with transformers","author":"Y Zhuang","year":"2024","journal-title":"arXiv Preprint"},{"key":"pone.0321291.ref030","article-title":"A systematic literature review on meta-heuristic based feature selection techniques for text classification","volume":"10","author":"SA Al-Shalif","year":"2024","journal-title":"PeerJ Comput Sci"},{"key":"pone.0321291.ref031","doi-asserted-by":"crossref","DOI":"10.7717\/peerj-cs.2336","article-title":"Adaptive classification of artistic images using multi-scale convolutional neural networks","volume":"10","author":"J Xiang","year":"2024","journal-title":"PeerJ Comput Sci"},{"key":"pone.0321291.ref032","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1007\/978-3-031-51518-7","article-title":"A diagnostic study of explainability techniques for text classification.","volume-title":"Accountable and explainable methods for complex reasoning over text","author":"P Atanasova","year":"2024"},{"issue":"1","key":"pone.0321291.ref033","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1007\/s00354-023-00227-0","article-title":"A CNN-LSTM-based hybrid deep learning approach for sentiment analysis on Monkeypox tweets","volume":"42","author":"KK Mohbey","year":"2024","journal-title":"New Gen Comput"},{"key":"pone.0321291.ref034","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1007\/978-981-97-3954-7_4","article-title":"Logistic regression.","author":"Y Geng","year":"2024","journal-title":"Practical Machine Learning Illustrated with KNIME"},{"issue":"1","key":"pone.0321291.ref035","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1007\/s11227-023-05441-7","article-title":"The effect of activation functions on accuracy, convergence speed, and misclassification confidence in CNN text classification: a comprehensive exploration","volume":"80","author":"RH Emanuel","year":"2024","journal-title":"J Supercomput"}],"updated-by":[{"DOI":"10.1371\/journal.pone.0332710","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000}}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0321291","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T17:27:47Z","timestamp":1749490067000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0321291"}},"subtitle":[],"editor":[{"given":"Michal","family":"Ptaszynski","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,6,9]]},"references-count":35,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,6,9]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0321291","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,9]]}}}