Enhanced Fake News Detection with Web Scraping Cross-Reference

View at publisher Summarise with VIRAT
Authors: Vinusha Uthayakumaran, Theebiga Vicknarajah, Theevika Sukirthan, Kanagasabai Thiruthanigesan, Gayana Fernando
Cited by: 0
References: 13

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The rapid proliferation of digital communication platforms has led to an alarming increase in the spread of fake news, threatening public trust, democratic processes, and social stability. To address this challenge, this paper presents a hybrid and multifunctional fake news detection system that integrates machine learning, natural language processing (NLP), and real-time cross-referencing with trusted news sources. The proposed system employs a Logistic Regression classifier trained on the ISOT dataset using TF-IDF vectorization, achieving a baseline accuracy of 97.9%. To enhance reliability, a cross-verification module leverages the Google Custom Search API to validate news content against authoritative sources such as BBC, CNN, The Guardian, AP News, and NPR. This duallayered approach increases overall accuracy to 98.55%, while providing transparent, verifiable evidence for each decision. The system supports both text and URL inputs, processes them through a robust preprocessing pipeline, and delivers real-time credibility assessments with confidence scores and reference links. Experimental results demonstrate the effectiveness of combining algorithmic prediction with external validation, significantly reducing false positives and improving accountability. With its lightweight architecture and high accuracy, the system offers a scalable and practical solution for combating misinformation across social media, journalism, education, and public policy domains.

Fields of Study & Subjects

Misinformation and Its Impacts Spam and Phishing Detection Hate Speech and Cyberbullying Detection

Publication details

Journal / source
IEEE International Conference on Industrial and Information Systems (ICIIS)
Pages
13–18
Publication date
16 January 2026
Language
EN