Fake news detection is important in the context of evolving events in today’s information-driven society. The current status of fake news detection literature focuses on static news articles, neglecting the challenges posed by the dynamic nature of evolving events. So, this research contributes to the existing literature by addressing the specific challenges of fake news detection within evolving events. By incorporating machine learning techniques and considering the evolving nature of events, our approach offers a scalable and adaptable solution for detecting fake news in evolving situations by incrementally updating training data and retraining the model. For the evaluation purpose, we also created a new fake news dataset on the Russia-Ukraine war from the Twitter postings. Extensive evaluation of our proposed model demonstrates that the model archives an overall accuracy of 94% in identifying fake/true news on evolving the Russia-Ukraine war event and outperforms two recent completing methods by a margin of 5%~10%.
Ferdush, Jannatul; Kamruzzaman, Joarder; Karmakar, Gour; Gondal, Iqbal; and Das, Raj, "Detecting Fake News of Evolving Events using Machine Learning: Case of Russia-Ukraine War" (2023). ACIS 2023 Proceedings. 122.