EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

BanglaNewsClassifier: A machine learning approach for news classification in Bangla Newspapers using hybrid stacking classifiers

Tanzir Hossain, Ar-Rafi Islam, Md Humaion Kabir Mehedi iD, Annajiat Alim Rasel iD, M Abdullah-Al-Wadud, Jia Uddin iD

PLOS One · 09.06.2025 · 20 (6) · e0321291

DOI: 10.1371/journal.pone.0321291 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 09.06.2025. Verfasst von Tanzir Hossain und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, BRAC University, Dhaka, Bangladesh. Hauptthemen laut MEDLINE: Machine Learning, Newspapers as Topic, Language. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: King Saud University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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’ 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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningNewspapers as TopicLanguageHumansSupport Vector MachineAlgorithmsDeep Learning

Autor:innen und Institutionen

  • Department of Computer Science and Engineering, BRAC University, Dhaka, Bangladesh.
  • Department of Software Engineering, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia.
  • AI and Big Data Department, Endicott College, Woosong University, Daejeon, Republic of Korea.

ORCID-Profile: Md Humaion Kabir Mehedi, Annajiat Alim Rasel, Jia Uddin

Förderung

  • King Saud University

Zitieren

APA

Hossain, T., Islam, A. R., Mehedi, M. H. K., Rasel, A. A., Abdullah-Al-Wadud, M., & Uddin, J. (2025). BanglaNewsClassifier: A machine learning approach for news classification in Bangla Newspapers using hybrid stacking classifiers. PLOS One, 20(6), e0321291. https://doi.org/10.1371/journal.pone.0321291

Vancouver

Hossain T, Islam AR, Mehedi MHK, Rasel AA, Abdullah-Al-Wadud M, Uddin J. BanglaNewsClassifier: A machine learning approach for news classification in Bangla Newspapers using hybrid stacking classifiers. PLOS One. 2025;20(6):e0321291. doi:10.1371/journal.pone.0321291

BibTeX
@article{Hossain2025,
  author = {Hossain, Tanzir and Islam, Ar-Rafi and Mehedi, Md Humaion Kabir and Rasel, Annajiat Alim and Abdullah-Al-Wadud, M and Uddin, Jia},
  title = {BanglaNewsClassifier: A machine learning approach for news classification in Bangla Newspapers using hybrid stacking classifiers},
  journal = {PLOS One},
  year = {2025},
  volume = {20},
  number = {6},
  pages = {e0321291},
  doi = {10.1371/journal.pone.0321291}
}
Kostenlos starten →