EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A WEB-BASED FAKE NEWS DETECTION SYSTEM USING HYBRIDIZED MACHINE LEARNING MODELS

ABDULSALAMI, B. A., MURAINAH, A. O., LAWAL, M., BAALE, A. A., AKINLOLU, A. O., BELLO, J.

Journal of Systematic and Modern Science Research · 17.04.2026

DOI: 10.70382/bejsmsr.v11i9.022 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Systematic and Modern Science Research, online erschienen am 17.04.2026. Verfasst von ABDULSALAMI und 11 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The widespread use of digital platforms has transformed the way news is distributed, but it has also made it easier for fake news to proliferate quickly, which has serious social and economic repercussions. Although there are manual fact-checking websites, they frequently have a large time lag, which lets misleading information spread extensively before it is refuted. This work uses machine learning (ML) to create an automated, web-based fake news detection system in order to overcome this difficulty. A dataset of 220 news articles (100 fake, 120 real) was sourced from reputable fact-checking organizations. Four ML algorithms namely Random Forest (RF), Decision Tree (DT), Naïve Bayes (NB), and Logistic Regression (LR) were implemented individually and subsequently hybridized using a stacking ensemble method. The hybrid model, which integrated RF, DT, and NB with LR as a meta-classifier, demonstrated superior performance, achieving an accuracy of 85.92%, an F1-score of 88.64%, a recall of 100%, and a precision of 79.59%. This best-performing model was integrated into a user-friendly web application using the Flask framework. The implemented system provides a timely and effective tool for classifying news authenticity, offering a proactive solution to mitigate the spread of misinformation. However, the study only focuses on professional fact-checking sources, which may limit generalizability to informal social media contexts.

Zitieren

APA

ABDULSALAMI, A., B., MURAINAH, O., A., LAWAL, M., BAALE, A., A., AKINLOLU, O., A., BELLO, & J. (2026). A WEB-BASED FAKE NEWS DETECTION SYSTEM USING HYBRIDIZED MACHINE LEARNING MODELS. Journal of Systematic and Modern Science Research. https://doi.org/10.70382/bejsmsr.v11i9.022

Vancouver

ABDULSALAMI, A. B, MURAINAH, O. A, LAWAL, M., et al. A WEB-BASED FAKE NEWS DETECTION SYSTEM USING HYBRIDIZED MACHINE LEARNING MODELS. Journal of Systematic and Modern Science Research. 2026. doi:10.70382/bejsmsr.v11i9.022

BibTeX
@article{ABDULSALAMI2026,
  author = {ABDULSALAMI and A., B. and MURAINAH and O., A. and LAWAL and M. and BAALE and A., A. and AKINLOLU and O., A. and BELLO and J.},
  title = {A WEB-BASED FAKE NEWS DETECTION SYSTEM USING HYBRIDIZED MACHINE LEARNING MODELS},
  journal = {Journal of Systematic and Modern Science Research},
  year = {2026},
  doi = {10.70382/bejsmsr.v11i9.022}
}
Kostenlos starten →