Detecting Fake News of Evolving Events using Machine Learning - Case of Russia-Ukraine War

Aug 5, 2026

Upload by Asher

Fake news detection is critical in information-driven environments where events evolve and information dynamics shift rapidly. Existing research often emphasizes static news, leaving gaps in addressing misinformation challenges created by unfolding, fluid situations. This work targets fake news detection in evolving events by integrating machine learning with incremental training updates and model retraining to remain scalable and adaptable. A new Russia–Ukraine war dataset is built from Twitter postings, achieving 94% overall accuracy and outperforming two recent methods by 5%–10%.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Abstract

Introduction

Problem background: evolving events and misinformation

Examples and motivation

Proposed approach

Machine learning with incremental retraining

Dataset construction

Russia–Ukraine war data from Twitter

Evaluation

Accuracy and comparison with baseline methods

Conclusion

Association for Information Systems AIS Electronic Library (AISeL) | ACIS 2023 Proceedings | Australasian (ACIS) | | --- | --- | | 12-2-2023
Detecting Fake News of Evolving Events using Machine Learning: Case of Russia-Ukraine War
Jannatul Ferdush
Centre for Smart Analytics Institute of Innovation, Science and Sustainability, Federation University, Australia, Australia, [jannatulferdush@students.federation.edu.au](jannatulferdush@students.federation.edu.au)
Joarder Kamruzzaman
Centre for Smart Analytics \& Institute of Innovation, Science and Sustainability, Federation University, Australia, Australia, [joarder.kamruzzaman@federation.edu.au](joarder.kamruzzaman@federation.edu.au)
Gour Karmakar
Centre for Smart Analytics \& Institute of Innovation, Science and Sustainability, Federation University, Australia, Australia, [gour.karmakar@federation.edu.au](gour.karmakar@federation.edu.au)
Iqbal Gondal
SCT, STEM College, RMIT University, Australia, Australia, [iqbal.gondal@rmit.edu.au](iqbal.gondal@rmit.edu.au)
Raj Das
Federation University, Australia, [r.das@federation.edu.au](r.das@federation.edu.au)
Follow this and additional works at: [https://aisel.aisnet.org/acis2023](https://aisel.aisnet.org/acis2023) | | Recommended Citation 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. [https://aisel.aisnet.org/acis2023/122](https://aisel.aisnet.org/acis2023/122) This material is brought to you by the Australasian (ACIS) at AIS Electronic Library (AISeL) . It has been accepted for inclusion in ACIS 2023 Proceedings by an authorized administrator of AIS Electronic Library (AISeL) . For more information, please [contact](contact elibrary@aisnet.org)[ elibrary@aisnet.org](contact elibrary@aisnet.org). Australasian Conference on Information Systems Jannatul et al. 2023, Wellington Detecting Fake News of Evolving Events Detecting Fake News of Evolving Events using Machine Learning: Case of Russia-Ukraine War Full research paper Jannatul Ferdush Centre for Smart Analytics & Institute of Innovation, Science and Sustainability, Federation University, Australia Email: [jannatulferdush@students.federation.edu.au](jannatulferdush@students.federation.edu.au) Joarder Kamruzzaman Centre for Smart Analytics & Institute of Innovation, Science and Sustainability, Federation University, Australia Email: [joarder.kamruzzaman@federation.edu.au](joarder.kamruzzaman@federation.edu.au) Gour Karmakar Centre for Smart Analytics & Institute of Innovation, Science and Sustainability, Federation University, Australia Email: [gour.karmakar@federation.edu.au](gour.karmakar@federation.edu.au) Iqbal Gondal SCT, STEM College, RMIT University, Australia Email: [iqbal.gondal@rmit.edu.au](iqbal.gondal@rmit.edu.au) Raj Das Centre for Smart Analytics & Institute of Innovation, Science and Sustainability, Federation University, Australia Email: [r.das@federation.edu.au](r.das@federation.edu.au) Abstract 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

FAQs

Why is fake news detection harder for evolving events than for static news?

Evolving events change quickly while misinformation can spread before verified facts are established, creating unique, time-sensitive detection challenges.

How does the proposed method adapt to evolving events over time?

It uses machine learning with incremental updates to training data and retrains the model to stay scalable and adaptable as the event evolves.

What dataset is used for evaluation, and how is it created?

A new fake news dataset is created for the Russia–Ukraine war using Twitter postings as the data source.

Aug 5, 2026

Upload by Asher