ContextFusion: Intelligent News Classification Using MPNet and XGBoost
International Journal of Scientific Research in Science and Technology · 20.06.2026 · 13 (3) · 1053-1058
DOI: 10.32628/ijsrst26133239 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Scientific Research in Science and Technology, online erschienen am 20.06.2026. Verfasst von Gauri Rajendra Zagade und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The rapid increase in digital news content has created a huge need for automatic organization and classification of huge amounts of generated text. Although already in the 1990s a lot of research was done on text classification by using machine learning (ML) for automatically organizing information, traditional methods like Naive Bayes and Support Vector Machines (SVM) have difficulty dealing with deeper levels of text analysis. In this paper, we propose a hybrid news classification method that integrates transformer-based semantic feature extraction and gradient boosting for text analysis. Specifically, we employ MPNet to generate the contextual embeddings of news articles and then use XGBoost to train a multiclass classifier for news classification. Our system is evaluated on the AG News dataset that consists of 120,000 news articles across four categories: Sports, Technology, Business, and World. The proposed system provides effective and efficient text analysis
Zitieren
APA
Zagade, G. R., & Kanavaje, T. D. (2026). ContextFusion: Intelligent News Classification Using MPNet and XGBoost. International Journal of Scientific Research in Science and Technology, 13(3), 1053-1058. https://doi.org/10.32628/ijsrst26133239
Vancouver
Zagade GR, Kanavaje TD. ContextFusion: Intelligent News Classification Using MPNet and XGBoost. International Journal of Scientific Research in Science and Technology. 2026;13(3):1053-1058. doi:10.32628/ijsrst26133239
BibTeX
@article{Zagade2026,
author = {Zagade, Gauri Rajendra and Kanavaje, Trupti Dilip},
title = {ContextFusion: Intelligent News Classification Using MPNet and XGBoost},
journal = {International Journal of Scientific Research in Science and Technology},
year = {2026},
volume = {13},
number = {3},
pages = {1053--1058},
doi = {10.32628/ijsrst26133239}
}
EUVIMED