Citation

Sen, Anik and Noman, Abdullah Yousuf and Rabbi, Riadul Islam and Hossen, Md. Jakir and Kumkum, Ananna Rashid (2026) Fake news detection: An introduction of hybrid machine learning model outperforming conventional classifiers. In: 5th International Conference on Mathematics, Engineering and Industrial Applications, ICoMEIA 2024, 26 October 2024 - 27 October 2024, Kedah.

Text Fake news detection_ An introduction of hybrid machine learning model outperforming conventional classifiers _ AIP Conference Proceedings _ AIP Publishing.pdf - Published Version Restricted to Repository staff only Download (264kB)

Abstract

The proliferation of fake news poses a significant challenge to modern information ecosystems. This paper introduces a hybrid machine learning model for fake news detection that integrates logistic regression, decision tree, and support vector machine (SVM) classifiers through a voting mechanism. The hybrid model is evaluated against conventional classifiers, specifically Multinomial Naive Bayes (MNB), Bernoulli Naive Bayes (BNB), and standalone logistic regression, using the WELFake dataset. Our hybrid model achieved an impressive accuracy of 96.19%, surpassing the performance of individual classifiers. The MNB and BNB models recorded accuracy scores of 89.46% and 85.45%, respectively, while the logistic regression model alone attained 94.23% accuracy. The experimental results demonstrate the robustness and superiority of our hybrid model in accurately identifying fake news, highlighting its potential impact on enhancing the reliability of information dissemination. The novelty of our research lies in the synergistic combination of diverse classifiers, which collectively leverage their unique strengths to produce a more accurate and reliable fake news detection system. This approach not only advances the state-of-the-art in fake news detection but also provides a practical framework for fu ture applications in various domains requiring high-stakes content verification.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Machine learning
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics
Divisions:	Faculty of Engineering and Technology (FET)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	04 May 2026 05:06
Last Modified:	04 May 2026 05:06
URII:	http://shdl.mmu.edu.my/id/eprint/15877

Downloads

Edit (login required)