Key points are not available for this paper at this time.
In response to the escalating threat of fake news on social media, this systematic literature review analyzes recent advancements in machine learning and deep learning approaches for its automated detection. Following the PRISMA guidelines, we examined 90 peer-reviewed studies published between 2020 and 2024 to evaluate model effectiveness, identify limitations, and highlight emerging trends. Our analysis shows that deep learning models, particularly transformer-based architectures such as BERT, consistently outperform traditional machine learning methods, often achieving high accuracy (Acc), precision (P), recall (R), and F1-score (F1). For instance, a BERT-based model reported up to 99.9% accuracy on the Kaggle fake news dataset and above 98% on other public datasets, including ISOT, Fake-or-Real, and D3. Similarly, the GANM model demonstrated robust performance on the FakeNewsNet dataset by integrating text and social features. Transfer learning and multimodal models that incorporate user behaviour and network information significantly improve detection in diverse and low-resource environments. However, challenges persist in terms of dataset quality, model interpretability, domain generalisability, and real-time deployment. This review also underscores the limited adoption of few-shot and zero-shot learning techniques, highlighting a promising direction for future research on handling emerging misinformation with minimal training data. To support practical deployment, we advocate the development of explainable, multilingual, and lightweight models with a greater emphasis on human-centred evaluation and ethical considerations. Our findings provide a foundation for researchers and practitioners aiming to build scalable, trustworthy, and context-aware fake news detection systems for global use.
Bashaddadh et al. (Wed,) studied this question.