Goodness: Intelligent System for Delivering Positive News with Sentiment Analysis and Summarization

In the modern digital landscape, individuals are inundated with vast amounts of news content, much of which carries a negative tone, contributing to heightened stress, anxiety, and emotional distress. To address this issue, the “Goodness” paper presents an advanced web-based system that collects, summarizes, and analyzes daily news articles, providing sentiment-annotated summaries through state-of-the-art machine learning and NLP techniques. The system follows a multi-stage pipeline. News articles are gathered from RSS feeds, processed using feed parser and trafilatura, and summarized via a BART-based model that condenses lengthy articles while preserving key details. Sentiment analysis is implemented through a dual-model approach. TextBlob filters neutral articles, and then a Logistic Regression model trained on the NLTK movie reviews dataset classifies the rest as positive or negative. A user-friendly Flask-based web interface with sentiment-based colour-coded highlights and ngrok for accessibility and scalability displays the summarised text. The “Goodness” technology improves digital news consumption by combining sentiment-aware summarisation with a real-time interactive interface to help consumers discern emotional tones and reduce the psychological impact of negative news. This study shows that AI-driven sentiment analysis can improve digital media consumption and public awareness.