International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 12 | Dec 2025
p-ISSN: 2395-0072
www.irjet.net
A Credibility Scoring Model for News Authenticity using SBERT/Logistic Regression Dr. C. P. Divate1, Mr. S. M. Patil2, Shreyash Potdar3, Kedar Potdar4, Tanmay Lad5, Nilesh Lokhande6, Raj Patil7 1Dean, Dept of Computer Engineering, Shri Ambabai Talim Sanstha’s Sanjay Bhokare Group of Institute
Miraj(poly), Maharashtra, India
2Lecturer, Dept of Computer Engineering, Shri Ambabai Talim Sanstha’s Sanjay Bhokare Group of Institute
Miraj(poly), Maharashtra, India
3,4,5,6,7Student Dept of Computer Engineering, Shri Ambabai Talim Sanstha’s Sanjay Bhokare Group of Institute
Miraj(poly), Maharashtra, India ---------------------------------------------------------------------***--------------------------------------------------------------------2. PROBLEM STATEMENT Abstract - The rapid spread of fake news on digital platforms has made it difficult to trust online information. Manual verification of news is slow and unreliable. This project presents A Credibility Scoring Model for News Authenticity using SBERT and Logistic Regression to automatically detect fake news. SBERT is used to capture the semantic meaning of news text, while Logistic Regression classifies the content as real or fake. The system also provides a credibility score showing prediction confidence. The model delivers accurate results and is integrated into an Android application for easy and real-time news verification.
The rapid expansion of digital news platforms and social media has made information easily accessible to users. However, this growth has also led to the widespread circulation of fake and misleading news. Such content can influence public opinion, create panic, and spread misinformation at a large scale. Manual verification of news authenticity is time-consuming and impractical due to the massive volume of online content. Existing fake news detection systems often rely on keywordbased or shallow text analysis techniques. These approaches fail to understand the contextual meaning of news articles, resulting in inaccurate predictions. Additionally, many systems only classify news as real or fake without providing any confidence level, making it difficult for users to judge the reliability of the result. Therefore, there is a need for an intelligent, accurate, and user-friendly system that can evaluate news credibility effectively.
Key Words: Fake News Detection, News Authenticity, Credibility Scoring, Sentence-BERT (SBERT), Logistic Regression, Natural Language Processing, Machine Learning, Text Classification
1. INTRODUCTION Through websites, social media, and mobile applications. While this makes information easily accessible, it also increases the risk of fake and misleading news reaching a large audience. False information can create confusion, influence public opinion incorrectly, and sometimes lead to serious social and economic consequences. As a result, verifying the authenticity of news has become an important challenge.
3. PROPOSED SOLUTION To overcome the identified challenges, this project proposes a credibility scoring model for news authenticity using Sentence-BERT (SBERT) and Logistic Regression. SBERT is used to convert news text into meaningful semantic embeddings that capture contextual information. These embeddings are then classified using Logistic Regression to determine whether the news is real or fake.
Traditional methods of fact-checking rely heavily on human effort, which is slow and cannot handle the massive amount of online content generated every day. To overcome this problem, automated systems based on machine learning and natural language processing are being widely explored. These systems can analyze news content and determine its credibility more efficiently.
In addition to binary classification, the system generates a credibility score based on prediction probability. This score helps users understand how confident the system is about the authenticity of the news. The trained model is integrated into an Android application, enabling real-time news verification through a simple and intuitive interface. The proposed solution is computationally efficient, scalable, and suitable for practical deployment, making it an effective tool for combating misinformation in digital media.
A Credibility Scoring Model for News Authenticity using SBERT and Logistic Regression, focuses on automatically identifying whether a news article is real or fake.
© 2025, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 921