Design and Implementation of a Fake News Detection System Using Machine Learning

Abstract

This project trains a machine learning model (logistic regression, SVM, and BERT) on a labelled dataset of Nigerian news articles to classify content as real or fake, and exposes the model via a web interface where users paste a URL or text. The study is organised into five chapters covering the introduction, review of related literature, system analysis and design, implementation and testing, and the summary, conclusion and recommendations.

Table of Contents

Chapter One: Introduction

1.1 Background to the Study

This project trains a machine learning model (logistic regression, SVM, and BERT) on a labelled dataset of Nigerian news articles to classify content as real or fake, and exposes the model via a web interface where users paste a URL or text.

1.2 Statement of the Problem

ML-based system that classifies Nigerian news articles and social media posts as real or fake. Existing approaches remain limited in reach, accuracy and ease of use, which creates the gap this study addresses.

1.3 Aim and Objectives

The aim of this study is to deliver a fake news detection system using machine learning. The specific objectives are to:

1. review existing literature and systems related to the study;
2. design and build the system using Python, scikit-learn, Transformers / BERT;
3. evaluate the results against the stated problem;
4. make recommendations for practice and further research.

1.4 Scope of the Study

Introduction: background to fake news detection, statement of the problem (viral misinformation on Nigerian social media drives ethnic tension and political instability), aim and objectives, research questions, scope, significance of the study, and definition of terms.