Fake News Detection Using Machine Learning Ensemble Methods

Abstract

The advent of the World Wide Web and the rapid adoption of social media platforms (such as Facebook and Twitter) paved the way for information dissemination that has never been witnessed in the human history before. With the current usage of social media platforms, consumers are creating and sharing more information than ever before, some of which are misleading with no relevance to reality. Automated classification of a text article as misinformation or disinformation is a challenging task. Even an expert in a particular domain has to explore multiple aspects before giving a verdict on the truthfulness of an article. In this work, we propose to use machine learning ensemble approach for automated classification of news articles. Our study explores different textual properties that can be used to distinguish fake contents from real. By using those properties, we train a combination of different machine learning algorithms using various ensemble methods and evaluate their performance on 4 real world datasets. Experimental evaluation confirms the superior performance of our proposed ensemble learner approach in comparison to individual learners.

Arabic Fake News Detection: Comparative Study of Neural Networks and Transformer‐Based Approaches

“…Another method [20] uses an ensemble learner approach to FND for English. Experimental results demonstrated the ensemble-based approach outperforms individual learners in the FND task.…”

Higher Classification of Fake Political News Using Decision Tree Algorithm Over Naive Bayes Algorithm

“…In paper (Agarwal et al 2020), feed forward neural networks which are developed using deep learning used to identify the fake news on social media which gives an accuracy of 97%. In paper (Ahmad et al 2020), Random forest and SVM(Support Vector Machine) machine learning algorithms are implemented to identify the fake news with accuracy of 91% and 96%. From these two papers we can observe that the Decision Tree algorithm proposed has better accuracy.…”

“…In paper (Shu et al 2017) a data mining procedure is performed on social media to collect the fake news and convert it into a dataset which can be used for analysis and is cited about 1057 times as reference for research. There are many other machine learning classifiers implemented earlier to detect fake news published or shared over social media has minimal accuracy (Ahmad et al 2020). In this paper, the implementing a machine learning classifier can provide a better accuracy for fake political news published over social media than the previously implemented classifiers.…”

“…The main aim of the study is to perform higher classification of fake political news by iterations on each group, one for fake news detection and other for true news detection using these two algorithms. Through the programming experiment that have performed N=10 iterations on each algorithm with sample size=10 to identify various scales of fake news and true news classification (Ahmad et al 2020). The G-power test is about 80%.…”

Contributions of Smart City Solutions and Technologies to Resilience against the COVID-19 Pandemic: A Literature Review

“…The free flow of information and the increasing availability of online communication platforms may, however, lead to the spread of misinformation that, when coupled with the pandemic, can create additional problems [70]. Machine learning techniques can be used to avoid this risk [71]. For instance, Google and Facebook have used such techniques to detect and delete misinformation [2].…”