News Classification at Scale: A Web Scraping and BERT-Based Approach
International Journal of Advanced Research in Science Communication and Technology · 22.06.2026 · 454
DOI: 10.48175/ijarsct-37158 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Advanced Research in Science Communication and Technology, online erschienen am 22.06.2026. Verfasst von Ms. Khushali Domadiya. Die Arbeit nennt 6 Literaturangaben.
Abstract (Originalsprache)
The quick growth of digital news media resulted in the accumulation of a tremendous amount of unstructured text data. The manual collection and classification of such data is not only inefficient but also hard to scale. The current research introduces a fully automated pipeline which combines web scraping with machine learning and deep learning techniques for large-scale news classification. The system encompasses automatic scraping, preprocessing, feature engineering, and classification through both traditional models and transformer-based architectures. The experiments conducted on the dataset of more than 20,000 articles show that the combination of automated scraping and the use of advanced NLP models like BERT has markedly improved the accuracy of classification as well as the efficiency of the whole operation. Furthermore, the paper presents the system architecture, experimental evaluation, challenges, and suggestions for future improvements.
Zitieren
APA
Domadiya, M. K. (2026). News Classification at Scale: A Web Scraping and BERT-Based Approach. International Journal of Advanced Research in Science Communication and Technology, 454. https://doi.org/10.48175/ijarsct-37158
Vancouver
Domadiya MK. News Classification at Scale: A Web Scraping and BERT-Based Approach. International Journal of Advanced Research in Science Communication and Technology. 2026:454. doi:10.48175/ijarsct-37158
BibTeX
@article{Domadiya2026,
author = {Domadiya, Ms. Khushali},
title = {News Classification at Scale: A Web Scraping and BERT-Based Approach},
journal = {International Journal of Advanced Research in Science Communication and Technology},
year = {2026},
pages = {454},
doi = {10.48175/ijarsct-37158}
}
EUVIMED