Detection of Fake Information Using a Hybrid Machine Learning and Natural Language Processing Framework

Abstract

This study focuses on applying machine learning techniques for fake news detection. It investigates the principles, methodologies, and algorithms used to identify fake news articles, their creators, and related topics across online social networks. In particular, a Naive Bayes classification model is proposed to classify news posts as either real or fake. The model is trained on labelled datasets and utilizes text pre-processing techniques such as tokenization, stop-word removal, and feature extraction methods like TF-IDF to enhance classification accuracy. The performance of the proposed model is evaluated using standard metrics including accuracy, precision, recall, and F1-score. Experimental results indicate that machine learning-based approaches, especially probabilistic classifiers such as Naive Bayes, can effectively address the fake news detection problem. Furthermore, performance can be improved by integrating advanced techniques such as ensemble learning, deep learning models, and natural language processing (NLP) methods.