1 of 5

DETECTING DIGITAL DECEPTION: A COMPARATIVE STUDY OF RULE-BASED AND MACHINE LEARNING APPROACHES FOR ONLINE MISINFORMATION DETECTION

ZANDILE DLADLA

4120815�BSC HONOURS COMPUTER SCIENCE�SUPERVISOR: MR ALLIE

2 of 5

PROBLEM & MOTIVATION

​

  • Rapid spread of misinformation online
  • Influences public opinion
  • Reduces trust in reliable sources
  • Manual fact-checking is too slow
  • Need for automated detection systems

3 of 5

PROPOSED SYSTEM

  • Input: Text (news / statements)
  • NLP preprocessing
  • TF-IDF feature extraction

Two approaches:

  • Rule-based detection
  • Machine Learning classifier
  • Output: Truthful / Misleading

​

4 of 5

SYSTEM ANALYSIS

Use Case Diagram

  • User inputs text
  • System processes and classifies
  • Results displayed

​

Class Diagram

  • Text Processor
  • Feature Extractor
  • Rule-Based Detector
  • ML Classifier
  • Result Module

5 of 5

PROJECT PLAN

Term 1: Analysis

Term 2: Design + Prototype

Term 3: Implementation

Term 4: Testing & Evaluation