AI-Powered News Aggrigator

Abstract

The rapid growth of digital media has improved access to information but also increased the spread of fake and misleading news. The AI Powered News Aggrigator is a web-based application designed to address these challenges by combining news aggregation and AI-based verification. The system collects real-time news from trusted sources using NewsAPI and provides personalized content based on user interests. By integrating Artificial Intelligence for authenticity verification, the platform promotes responsible information consumption while enhancing user experience. This project demonstrates the practical application of AI, API integration, and full-stack web development for both academic and real-world use.

Introduction

The rapid growth of digital media has transformed how news is produced and consumed, but it has also accelerated the spread of fake and misleading information. Traditional news aggregation platforms primarily collect articles using RSS feeds, keywords, and metadata, focusing on retrieval rather than verifying credibility. These systems often lack personalization, overwhelm users with irrelevant content, and fail to assess authenticity, making it difficult for users to distinguish between real and fake news.

Existing technologies face several limitations: they do not automatically verify content credibility, rely on slow manual verification processes, lack scalability, provide little personalization, and do not offer explanations or confidence scores regarding news authenticity.

To address these issues, the proposed AI-Powered News Aggregator and Fake News Detection System integrates news aggregation with artificial intelligence-based verification. The system collects real-time news through APIs, preprocesses and extracts features from text, and applies machine learning and natural language processing (NLP) techniques to classify news as real or fake. Verified articles are categorized and personalized based on user interests, and credibility warnings are displayed for suspicious content. All data is stored in a database for continuous improvement.

The dataset used includes 5,000–10,000 articles consisting of both real and fake news, divided into 70% training and 30% testing data. Experimental results show that the system successfully provides secure access, real-time news search, fake news detection, and user interaction features.

Future enhancements include integrating advanced transformer models, adding explainable AI and source credibility scoring, enabling multilingual support, incorporating sentiment analysis and summarization, developing a mobile app, improving scalability and security, and implementing an admin dashboard for monitoring and governance.

Conclusion

The AI-Powered News Aggregator and Fake News Detection System was developed to tackle information overload and the spread of misleading news. It combines real-time news aggregation, personalized content delivery, and AI-based verification in a single user-friendly platform. Using NewsAPI, the system delivers relevant news based on user interests, improving engagement and usability. Secure authentication ensures safe access and protects user data. The fake news detection module analyzes news credibility and provides confidence scores with explanations, helping users make informed decisions. The AI-powered search feature enables quick and efficient news retrieval. Built with modern technologies like Flask and SQLAlchemy, the system is reliable and scalable. Overall, the project demonstrates how Artificial Intelligence can help combat misinformation and improve digital news consumption.

References

[1] K. Shu, A. Sliva, S. Wang, J. Tang, and H. Liu, “Fake News Detection on Social Media: A Data Mining Perspective,” ACM SIGKDD Explorations Newsletter, vol. 19, no. 1, pp. 22–36, 2017. [2] H. Allcott and M. Gentzkow, “Social Media and Fake News in the 2016 Election, ”Journal of Economic Perspectives, vol. 31, no. 2, pp. 211–236, 2017. [3] N. J. Conroy, V. L. Rubin, and Y. Chen, “Automatic Deception Detection: Methods for Finding Fake News ,”Proceedings of the Association for Information Science and Technology, vol. 52, no. 1, pp. 1–4, 2015. [4] V. L. Rubin, Y. Chen, and N. J. Conroy, “Deception Detection for News: Three Types of Fakes, ”Proceedings of the Association for Information Science and Technology, 2015. [5] K. Shu, D. Mahudeswaran, and H. Liu, “FakeNewsNet: A Data Repository with News Content, Social Context and Dynamic Information for Fake News Research, ”Proceedings of the International AAAI Conference on Web and Social Media (ICWSM), 2018. [6] S. Ruchansky, S. Seo, and Y. Liu, “CSI: A Hybrid Deep Model for Fake News Detection, ”Proceedings of the ACM Conference on Information and Knowledge Management (CIKM), pp. 797–806, 2017. [7] W. Y. Wang, “Liar, Liar Pants on Fire: A New Benchmark Dataset for Fake News Detection ,”Proceedings of the Association for Computational Linguistics (ACL), 2017. [8] P. Baly, G. Karadzhov, D. Alexandrov, J. Glass, and P. Nakov, “Predicting Factuality of Reporting and Bias of News Media Sources, ”Proceedings of EMNLP, 2018. [9] T. Zhou and H. Zafarani, “Fake News: A Survey of Research, Detection Methods, and Opportunities, ”ACM Computing Surveys, vol. 53, no. 5, 2020. [10] S. Vosoughi, D. Roy, and S. Aral, “The Spread of True and False News Online,” Science, vol. 359, no. 6380, pp. 1146–1151, 2018.

Copyright

Copyright © 2026 H. Hanspal , Aayusha Nikam, Shruti Ranjve, Vedika Sangle. This 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.