|International Journal of Applied Information Systems|
|Foundation of Computer Science (FCS), NY, USA|
|Volume 12 - Number 41|
|Year of Publication: 2023|
|Authors: Timothy Moses, Henry Egaga Obi, Christopher Ifeanyi Eke, Jeffrey Agushaka|
Timothy Moses, Henry Egaga Obi, Christopher Ifeanyi Eke, Jeffrey Agushaka . Enhancing Fake News Identification in Social Media through Ensemble Learning Methods. International Journal of Applied Information Systems. 12, 41 ( Sep 2023), 1-22. DOI=10.5120/ijais2023451949
The proliferation of deliberately misleading information, commonly known as fake news, poses a significant challenge in shaping public opinions. This paper presents a cutting-edge methodology for effectively identifying and combating fake news by harnessing the power of ensemble learning techniques. Recognizing the widespread influence of fake news and its detrimental societal effects, there is an urgent need for robust and adaptable identification models. Existing approaches often suffer from biases and lack adaptability due to their reliance on single algorithms or limited datasets. To address these limitations, the study introduces an ensemble learning model that incorporates a diverse range of algorithms, enhancing accuracy and adaptability across various fake news contexts. Leveraging a benchmark dataset, the established model attained an exceptional accuracy rate of 97.86% using the test dataset, outperforming existing architectures. Through this research, the researchers aim to mitigate the adverse impact of fake news on social media platforms and provide a more reliable means of content verification.