Artificial Intelligence and Big Data Analytics for the Detection of Fake News on Social Media

The advent of social media has facilitated the rapid dissemination of information, prompting news broadcasting organisations to utilise these platforms for wider audience outreach. While this shift has brought substantial benefits to both organisations and individuals, the proliferation of generative Artificial Intelligence has given rise to an increase in false news and deceptive content, often driven by financial incentives. Such misleading information, widely disseminated on social media, presents opportunities for cybercriminals to engage in activities such as extortion, cyberbullying, and the strategic enhancement of social engineering tactics. These activities are integral components of the footprinting and reconnaissance stages in the lifecycle of cyberattacks. The spread of fake and deceptive content necessitates intensified research into the identification and mitigation of fake and deceptive content. This study evaluates the efficacy of Artificial Intelligence (AI) and Big Data Analytics (BDA) for the detection of fake news on social media using Naíve Bayes (NB), Random Forest (RF), Logistic Regression (LR), and Support Vector Machine (SVM) models. In society at large, it is pertinent to spot fake news to prevent disastrous outcomes when certain information is shared. Out of the four machine learning (ML) techniques applied, the SVM model outperformed others with accuracy and precision of 0.81 and 0.82, respectively. The LR model showed similar precision and the highest recall. These methods provide a foundation for reliable automated fake news detection tools.