GENAI DRIVEN TEXT SUMMARIZATION FOR NEWS AGGREGATION

Abstract

The GENAI-Driven Text Summarization for News Aggregation project is an advanced application of Generative Artificial Intelligence designed to address the growing challenge of information overload caused by the rapid expansion of digital news media. In today’s digital world, users are exposed to massive amounts of news content from multiple sources, making it difficult to identify important information and extract meaningful insights efficiently. This project provides an intelligent solution by using Large Language Models (LLMs) to automatically summarize, organize, and analyze complex news articles in a concise and structured manner. The system is developed using the Streamlit framework and powered by Llama 3.1 integrated through the Groq API to enable high-speed and low-latency AI processing. Unlike traditional text summarization systems that simply shorten articles, the proposed platform acts as an intelligent news aggregation and analysis dashboard capable of transforming unstructured news data into structured and insightful information. The system automatically extracts important topics, geopolitical entities, sentiment trends, key highlights, and contextual summaries from news content. The core architecture utilizes a dual-engine approach consisting of an Analysis Engine and an Investigation Engine. The Analysis Engine processes news articles and converts them into structured JSON data while identifying important entities, keywords, sentiment patterns, and topic relationships. The Investigation Engine enables users to perform deeper analysis and detailed exploration of specific news topics through an interactive session-based interface. The application also integrates Plotly visualizations to generate graphical representations such as sentiment analysis charts, trend visualizations, and geographic news distribution maps, providing users with a multidimensional understanding of global events.