Mitigating Misinformation A Machine Learning Model For Detecting Fake

Bonisiwe Shabane

-Dec 6, 2025, 12:40 AM

mitigating misinformation a machine learning model for detecting fake

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.© Copyright 2025 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions. Mouratidis, D.; Kanavos, A.; Kermanidis, K. From Misinformation to Insight: Machine Learning Strategies for Fake News Detection. Information 2025, 16, 189. https://doi.org/10.3390/info16030189

Mouratidis D, Kanavos A, Kermanidis K. From Misinformation to Insight: Machine Learning Strategies for Fake News Detection. Information. 2025; 16(3):189. https://doi.org/10.3390/info16030189 Mouratidis, Despoina, Andreas Kanavos, and Katia Kermanidis.

2025. "From Misinformation to Insight: Machine Learning Strategies for Fake News Detection" Information 16, no. 3: 189. https://doi.org/10.3390/info16030189 Mouratidis, D., Kanavos, A., & Kermanidis, K. (2025).

From Misinformation to Insight: Machine Learning Strategies for Fake News Detection. Information, 16(3), 189. https://doi.org/10.3390/info16030189 Scientific Reports , Article number: (2025) Cite this article We are providing an unedited version of this manuscript to give early access to its findings. Before final publication, the manuscript will undergo further editing.

Please note there may be errors present which affect the content, and all legal disclaimers apply. The widespread dissemination of misinformation on online platforms has become a significant societal challenge, influencing public opinion, political landscapes, and social stability. Traditional rule-based and statistical methods for fake news classification often struggle to generalize across different datasets due to the evolving nature of misinformation. To address this, deep learning and natural language processing (NLP) techniques have emerged as effective solutions for detecting deceptive content. In this study, a novel fake news classification framework is proposed, integrating Transformer-based feature extraction with an XGBoost classifier. The methodology leverages RoBERTa embeddings, Term Frequency-Inverse Document Frequency (TF-IDF)-based tokenization, and metadata processing to capture both linguistic and contextual cues essential for accurate classification.

The model is trained and evaluated on the PolitiFact and GossipCop datasets, achieving state-of-the-art performance with an accuracy of 0.9930 and 0.9764, respectively. Comparative analysis with existing methods demonstrates the effectiveness of our approach in improving precision, recall, and F1-score. The findings underscore the importance of combining deep learning-based feature extraction with ensemble learning techniques for robust and scalable fake news detection. The source code supporting the findings of this study is publicly available at our GitHub repository: https://github.com/aintlab/hybrid-fake-news-detector. Additional data or materials can be provided upon reasonable request. For further information, please contact the corresponding authors.

Shu, K., Sliva, A., Wang, S., Tang, J. & Liu, H. Fake news detection on social media: A data mining perspective. SIGKDD Explorations 19, 22–36. https://doi.org/10.1145/3137597.3137600 (2017). Part of the book series: Communications in Computer and Information Science ((CCIS,volume 2502))

Included in the following conference series: This project explores the application of machine learning models and advanced natural language processing (NLP) techniques to detect and mitigate misinformation, commonly referred to as “fake news.“ As misinformation becomes increasingly prevalent, public trust... The spread of false information impairs individuals’ ability to make well-informed decisions, ultimately distorting public discourse and shaping opinions based on inaccurate narratives. This study aims to examine the role of machine learning in combating misinformation and to develop a tool that enables individuals to verify the credibility of news content, thereby addressing the growing distrust between... Leveraging Amazon Web Services (AWS), including Simple Storage Service (S3) for data management and SageMaker for model training and inference, this research establishes a robust foundation for misinformation detection. Key methodologies include the implementation of Long Short-Term Memory (LSTM) networks and the XGBoost algorithm to enhance the accuracy of fake news classification.

By tackling the challenges associated with misinformation, this project aspires to contribute to a more informed society. However, ongoing research remains essential to further refine detection methods and safeguard media consumers against deceptive content. This is a preview of subscription content, log in via an institution to check access. Tax calculation will be finalised at checkout Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to... The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material.

If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from... To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. Fake news and disinformation (FNaD) are increasingly being circulated through various online and social networking platforms, causing widespread disruptions and influencing decision-making perceptions. Despite the growing importance of detecting fake news in politics, relatively limited research efforts have been made to develop artificial intelligence (AI) and machine learning (ML) oriented FNaD detection models suited to minimize supply... Using a combination of AI and ML, and case studies based on data collected from Indonesia, Malaysia, and Pakistan, we developed a FNaD detection model aimed at preventing SCDs. This model based on multiple data sources has shown evidence of its effectiveness in managerial decision-making.

Our study further contributes to the supply chain and AI-ML literature, provides practical insights, and points to future research directions. Keywords: Fake news, Disinformation, Misinformation, Artificial intelligence, Machine learning, Supply chain disruptions, Effective decision making The increased scholarly focus has been directed to fake news detection given their widespread impact on supply chain disruptions, as was the case with the COVID-19 vaccine. Fake news and misinformation are highly disruptive, which create uncertainty and disruptions not only in society but also in business operations. Fake news and disinformation-related problems are exacerbated due to the rise of social media sites. Regarding this, using artificial intelligence (AI) to counteract the spread of false information is vital in acting against disruptive effects (Gupta et al., 2021).

It has been observed that fake news and disinformation (FNaD) harm supply chains and make their operation unsustainable (Churchill, 2018). According to research, fake news can be classified into two distinct concepts of misinformation and disinformation (Petratos, 2021; Allcott & Gentzkow, 2017) defined fake news as “news articles that are intentionally and verifiably false,... 213). According to Wardle (2017), misinformation refers to “the inadvertent sharing of false information”, while disinformation can be defined as “the deliberate creation and sharing of information known to be false”. Among the negative consequences that fake news can have for companies are loss of sponsorships, reduced credibility, and loss of reputation which can adversely affect performance (Di Domenico et al., 2021). In such a context AI is shaping decision-making in an increasing range of sectors and could be used to improve the effectiveness of fake news timely detection and identification (Gupta et al., 2021).

Whereas many new efforts to develop AI-based fake news detection systems have concentrated on the political process, the consequences of FNaD on supply chain operations have been relatively underexplored (Gupta et al., 2021). Kaplan and Haenlein (2019) addressed AI “as a system’s ability to interpret external data correctly, to learn from such data, and to use those learnings to achieve specific goals and tasks through flexible adaptation”... Although emerging technologies such as AI may sometimes have negative effects, they can be utilized to combat disinformation. As scholarship is showing increasing interest in how AI can improve operationally and supply chain efficiencies (Brock & von Wangenheim, 2019), researchers have recently called for more studies on how organizational strengths and the... Fake news has considerable negative effects on firms’ operations, such as repeated disruptions of supply chains (Churchill, 2018). FNaD influence the use of a company’s product or services (Zhang et al., 2019; Sohrabpour et al., 2021) argued that leveraging AI to improve supply chain operations will likely improve firms’ planning, strategy, marketing,...

Mitigating Misinformation A Machine Learning Model For Detecting Fake

People Also Search

A Not-for-profit Organization, IEEE Is The World's Largest Technical Professional

Mouratidis D, Kanavos A, Kermanidis K. From Misinformation To Insight:

2025. "From Misinformation To Insight: Machine Learning Strategies For Fake

From Misinformation To Insight: Machine Learning Strategies For Fake News

Please Note There May Be Errors Present Which Affect The