Open Access Open Access  Restricted Access Subscription Access

FACT CHECKING

B DEEKSHITHA PRASANNA, Dr. CRK Reddy, Ms. N Musrat Sulthana, K Sunitha

Abstract


The widespread dissemination of misinformation across digital platforms has led to an urgent need for scalable and effective fake news detection systems. This project presents a real-time fake news detection model that leverages machine learning and Natural Language Processing (NLP) to determine the authenticity of news content. The system classifies news articles into two categories: Real or Fake.

Our methodology includes collecting labeled datasets (fake.csv and true.csv), preprocessing and cleaning the news content, and extracting semantic features using Sentence-BERT (SBERT) embeddings (all-MiniLM-L6-v2). These embeddings capture the contextual meaning of text, enabling more accurate classification. A Logistic Regression model is trained on these embeddings for binary classification. The application is deployed as an interactive headlines or articles and receives instant classification results, including confidence score.

Full Text:

PDF

References


"Detection of Fake News from Social Media Using Support Vector Machine Learning Algorithms" by M. Sudhakar and K.P. Kaliyamurthie (2024).

"Detection of Fake News Campaigns Using Graph Convolutional Networks" by Dimitrios Michail and Nikos Kanakaris (2022).

"Claim Detection for Automated Fact- checking: A Survey on Monolingual, Multilingual, and Cross-Lingual Research" by Rrubaa Panchendrarajan and Arkaitz Zubiaga (2024).


Refbacks

  • There are currently no refbacks.