AI MODEL BASED ON FAKE NEWS DETECTION SYSTEM
Abstract
The proliferation of fake news on social media and online platforms has posed significant
challenges to society, leading to misinformation, confusion, and the erosion of trust in reliable
information sources. This study presents the development of an AI-based fake news detection
system, leveraging advanced machine learning and natural language processing (NLP) techniques
to identify and classify misleading or false information. By addressing the growing impact of fake
news, the system aims to assist users, organizations, and policymakers in detecting and mitigating
the spread of misinformation effectively.
The problem lies in the difficulty of distinguishing between authentic and false news due to the
sheer volume of information and the sophistication of fabricated content. Current manual methods
for fact-checking are time-consuming and prone to bias, highlighting the urgent need for automated
tools. This project seeks to solve this problem by designing a system capable of analyzing textbased news articles and providing accurate classifications, thereby promoting informed decisionmaking and fostering trust in information dissemination.
To achieve this, the study employs a systematic methodology, beginning with data collection and
preprocessing, followed by feature extraction using NLP techniques. The design integrates
supervised machine learning models such as logistic regression, support vector machines (SVM), or
deep learning architectures like transformers to train the detection system. The implementation
focuses on creating a user-friendly interface where users can input news articles for real-time
analysis. The system is evaluated through precision, recall, F1-score metrics, and comparison with
existing solutions to measure its accuracy and reliability in real-world scenarios.
In conclusion, the AI-based fake news detection system represents a significant step forward in
combating the spread of misinformation. By combining advanced AI technologies with user-centric
design, the system offers a scalable and efficient solution for detecting fake news.
Full-Text Access Notice
In accordance with the NERD Policy on promoting peer-reviewed publication, public access to the full text of a project, thesis or dissertation is restricted for three years, allowing the author and supervisors sufficient time to pursue peer-reviewed publication.
During this period, researchers with legitimate academic or research purposes may request authorisation directly from the author to enable NERD to release the indexed full texts of the work using the form below.