Fake News Detection Using Input based News Retrieval And RAG

    The rapid spread of information through social media has increased the prevalence of fake news, which can influence public opinion and reduce trust in reliable sources. Traditional detection methods rely on static datasets and basic textual analysis, making them less effective against sophisticated and evolving misinformation.  To overcome these challenges, this project proposes a Retrieval-Augmented Generation (RAG) based fake news detection system that combines real-time information retrieval with Large Language Models. The system verifies news using trusted sources, improves accuracy, and provides explainable results. Its scalable design and use of evaluation metrics ensure an efficient and reliable solution for combating misinformation

1.    Achiam, J.,  Adler, S.,   Agarwal, S.,  Ahmad, L.,  Akkaya, I., Aleman, F. L.,  Almeida, D.,  Altenschmidt, J.,     Altman, S., Anadkat, S.,  et al. (2023).    GPT-4 technical   report.  arXiv preprint arXiv:2303.08774. 2.     Ahmed, H., Traore, I., & Saad, S. (2017). Detection of online fake   news   using n-gram  analysis  and  machine     learning techniques. In Intelligent, Secure, and Dependable Systems in Distributed  and  Cloud  Environments:    Firs   t International Conference, ISDDC 2017, Vancouver, BC, Canada, October 26–28, 2017, Proceedings 1 (pp. 127–138). Springer. 3.    Ahmed, H., Traore, I., & Saad, S. (2018). Detecting opinion spams and fake news using text classification. Security and Privacy, 1(1), e9. 4.    Allcott, H., & Gentzkow, M. (2017). Social media and fake news   in      the  2016  election.  Journal   of        Economic Perspectives, 31(2), 211–236. 5.    Altheneyan, A., & Alhadlaq, A. (2023).     Big   data   ML-based fake newsdetection using distributed learning. IEEE Access, 11, 29447–29463. 6.    Barbon, R., & Akabane, A. (2022). Towards transfer learning techniquesBERT, DistilBERT, BERTimbau, and DistilBERTimbau for automatic text classification from different languages: A case study. 7.    Blackledge, C., & Atapour-Abarghouei, A. (2021). Transforming fake news: Robust generalisable news classification using transformers. In 2021 IEEE International Conference on Big Data (Big Data) (pp. 3960–3968). IEEE. 8.    Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877–1901. 9.    Budi, I., & Suryono, R. R. (2023). Application of named entity recognition method for Indonesian datasets: A review. Bulletin of Electrical Engineering and Informatics, 12(2), 969–978. 10. Conroy, N., Rubin,  V., &     Chen, Y  . (2015)   . Automatic deception   detection:    Methods   for   finding    fake   news. Proceedings of the Association for Information Science and Technology, 52(3), 1–4.