AI-Powered News Recommendation System Using Generative AI and Natural Language Processing

Pallapu Ravi Teja, Mrs. B. Shireesha

Generative AI; Natural Language Processing; News Recommendation System; Semantic Search; Personalization; Django; Conversational Interface.

The rapid growth of digital news content has created significant challenges in information discovery, leading to issues such as information overload and reduced user engagement. Traditional news recommendation systems rely on keyword-based search, manual categorization, or popularity-driven approaches, which often fail to accurately capture user intent and deliver personalized content. To address these limitations, this paper proposes an AI-Powered News Recommendation System that utilizes Generative AI and Natural Language Processing (NLP) to provide context-aware and user-centric recommendations. The system integrates Google’s Gemini generative AI model within a Django-based web application, enabling users to interact through natural language queries via a conversational interface. The generative AI model interprets user intent, extracts semantic meaning, and maps queries to relevant news categories, allowing efficient retrieval of articles from a structured database. This approach effectively bridges the gap between unstructured user input and structured data storage, thereby improving recommendation accuracy and relevance. The system follows a three-tier architecture consisting of the presentation layer, application layer, and data layer. The backend is implemented using Python and Django, while the frontend is developed using HTML, CSS, JavaScript, and Bootstrap to ensure a responsive user experience. Experimental results demonstrate that the proposed system reduces information overload, improves recommendation precision, and enhances overall user satisfaction. The integration of generative AI enables flexible, intelligent, and context-driven query processing, making the system more effective than conventional approaches.

[1] C. D. Manning, P. Raghavan, and H. Schütze, Introduction to Information Retrieval. Cambridge University Press, 2008.
[2] T. Brown et al., “Language models are few-shot learners,” Advances in Neural Information Processing Systems, vol. 33, pp. 1877–1901, 2020.
[3] M. Pazzani and D. Billsus, “Content-based recommendation systems,” in The Adaptive Web, Springer, 2007, pp. 325–341.
[4] P. Resnick and H. R. Varian, “Recommender systems,” Communications of the ACM, vol. 40, no. 3, pp. 56–58, 1997.
[5] P. Lops, M. de Gemmis, and G. Semeraro, “Content-based recommender systems: State of the art and trends,” in Recommender Systems Handbook, Springer, 2011, pp. 73–105.
[6] A. Ricci, L. Rokach, and B. Shapira, Recommender Systems Handbook, 2nd ed. Springer, 2015.
[7] J. Devlin et al., “BERT: Pre-training of deep bidirectional transformers for language understanding,” Proceedings of NAACL-HLT, pp. 4171–4186, 2019.
[8] A. Vaswani et al., “Attention is all you need,” Advances in Neural Information Processing Systems, 2017.
[9] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT Press, 2016.
[10] G. Adomavicius and A. Tuzhilin, “Toward the next generation of recommender systems,” IEEE Transactions on Knowledge and Data Engineering, vol. 17, no. 6, pp. 734–749, 2005.
[11] J. Han, M. Kamber, and J. Pei, Data Mining: Concepts and Techniques, 3rd ed. Morgan Kaufmann, 2011.
[12] A. Holovaty and J. Kaplan-Moss, The Definitive Guide to Django. Apress, 2009.
[13] S. Bird, E. Klein, and E. Loper, Natural Language Processing with Python. O’Reilly Media, 2009.
[14] D. Jurafsky and J. H. Martin, Speech and Language Processing, 3rd ed., Pearson, 2020.
[15] S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, 3rd ed. Pearson, 2010.