Authors:
S. Rubin Bose, R. S. Gaayathri, J. Angelin Jeba, Judy Flavia, R. Regin, P. Paramasivan

Addresses:
Department of Computer Science and Engineering, SRM Institute of Science and Technology, Ramapuram, Chennai, Tamil Nadu, India. Department of Electronics and Communication Engineering, S.A. Engineering College, Chennai, Tamil Nadu, India. Department of Research and Development, Dhaanish Ahmed College of Engineering, Chennai, Tamil Nadu, India.

Abstract:

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.

Keywords: Natural Language Processing; Sentiment Analysis; Text Summarization; Flask Web Application; Negative Content; Pre-Trained Language Models; Decision-Making; NLP Community.

Received on: 01/06/2024, Revised on: 29/07/2024, Accepted on: 18/09/2024, Published on: 03/12/2024

DOI: 10.69888/FTSCL.2024.000281

FMDB Transactions on Sustainable Computer Letters, 2024 Vol. 2 No. 4, Pages: 217-231

• Views : 66
• Downloads : 7

Download PDF