Ensuring Cybersecurity While Leveraging Social Media as a Data Source for Internet of Things Applications

Abstract

Social media and the Internet of Things (IoT) have revolutionized the way we communicate and access information. However, the integration of these technologies also poses significant cybersecurity risks. This paper explores the challenges of using social media data in IoT applications and proposes strategies to ensure the protection of sensitive information. The aim is to strike a balance between leveraging the benefits of social media data and ensuring that adequate measures are taken to secure this information. The authors outline the importance of using secure data-sharing protocols, implementing data privacy policies, and conducting regular security audits to minimize the risk of cyberattacks. In this study, we compared the performance of four popular classifier models: Multinomial Naive Bayes, Bernoulli Naive Bayes, Gaussian Naive Bayes, and Logistic Regression, on a dataset of news articles. Our results showed that the best model for fake news prediction was Logistic Regression, achieving an accuracy of 0.99%. This research provides a promising solution for the automated detection of fake news, which could potentially be used in real-world applications to combat the spread of misinformation.