2025

Permanent URI for this collection

https://escholar.umt.edu.pk/handle/123456789/5171

Browse

Browsing 2025 by Author "Abdullah Rehman"

Now showing 1 - 1 of 1
  • Thumbnail Image
    Item
    Web-based fake news detection application
    (UMT.Lahore, 2025) Sikandar Farooq; Musfira Rabia Ramzan; Maryam Iftikhar; Abdullah Rehman
    Under the current scenario, one of the main problems is the spread of misinformation through fake news in our society. Hence, we created a Web Based Application that brings artificial intelligence power to detect news articles and classify them as "REAL" or "FAKE". Our application achieves an accu racy of 99.65% by using machine learning techniques such as logistic regression, Random forests, and the deep learning model BERT. Therefore, it creates strong detection on each news input based on its content and finds it as "REAL" or "FAKE". It do so mostly by buildings such machine learning techniques, the following application can do a great job at 99.65% accuracy. This process includes developments like learning algorithms such as logistic regression, Random forests, and deep learning such as BERT. The technology makes it possible to test news content with a much higher precision. Misinformed fake news has is a major problem in society today. A web-based Application is to find a solution to this problem by using the power of AI to read and classify news articles as “REAL” or “FAKE”. Using some machine learning techniques like logistic regression, Random forests, and a deep learning model BERT, the application has chieved an accuracy of 99.65% and can process large document collections. hese technologies enable the application to test the content of the news at very high precision to ensure its reliability. This project has integrated the Scrum methodology, which uses an agile, collaborative, and iterative approach, which gave us flexibility within the development phases of the application. Besides its main purpose of verifying news, the app has a number of features that seek to enhance user experience such as a news blog that provides articles and viewpoints about other subjects, social media posts analysers, as well as feedback tools that enable users to voice their suggestions for the improvement of the app. Everyone can access the application through http://newsverifier.surge.sh/, which makes it easier for people to verify news and stay up to date. This report offers an in-depth review of the project beginning from the basic explanation which was our motivation to tackle misinformation and build trust in online media. It explains in detail how we crafted the design and developed it, the ethodologies we applied, and all the problems we expect to face. An ntegrated technology aimed at combining user-friendly features will allow users to make sensible information consumption decisions and lend credence to an ecosystem that supports trusted digital information. We hope to mitigate the impact of fake news significantly and foster a community of individual responsibility