Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{188071,
        author = {TEJASWINI C N and TEJAS and DARSHAN SURAMPALLY and JUSTIN SEBASTIAN THOMAS and DHIVYA V},
        title = {AI – Powered Local News Aggregator},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {920-924},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=188071},
        abstract = {AI-powered local news aggregation system designed to provide personalized, diverse, and semantically relevant news to users by combining modern NLP and vector retrieval technologies. The system uses BERT embeddings for contextual sentence representation, FAISS for high-speed similarity search, MMR (Maximal Marginal Relevance) for balancing relevance and diversity, and a Theoretical Topic Jump Model for smooth topic transitions in the news feed. The architecture integrates a React-based frontend with a REST API backend for fast and interactive delivery. The objective of this work is to overcome the limitations of keyword-based news engines by using transformer models and vector indexing to provide more meaningful and diverse recommendations.},
        keywords = {— AI, BERT, FAISS, News Aggregation, Recommendation System, MMR, Topic Jump.},
        month = {December},
        }