Fake news, characterized by false information disseminated intentionally with malicious intent, has become a critical societal issue. Its impact spans political, economic, and social domains, fueled by the rapid proliferation of digital communication channels, particularly social media. To combat this menace, researchers have turned to automated mechanisms for detection, leveraging machine learning algorithms and curated datasets. In this exploratory research, the landscape of machine learning algorithms is employed in identifying fake news. Notably, the research focus on algorithms such as the Bidirectional Encoder Representations from Transformers (BERT) and Convolutional Neural Network (CNN) respectively. However, most of these studies rely on controlled datasets lacking real-time information from social networks—the very platforms where disinformation thrives. The findings underscore the need for research in social network environments, where fake news spreads most prolifically. Additionally, future investigations should extend beyond political news, considering hybrid methods that combine NLP and deep learning techniques. This study serves as a valuable resource for researchers, practitioners, and policymakers seeking insights into the evolving landscape of the ability to combat fake news effectively.

Deep Learning Fake News Detection Natural Language Processing Pre-Trained Embedding Text Classification Multimodal Datasets Evaluation Metrics.