Paper Contents
Abstract
The widespread use of digital platforms has made the sharing of information easier than ever before, but it has also led to the uncontrolled circulation of misinformation, commonly known as fake news. Such content can misguide readers and impact public trust, politics, and social harmony. Manual verification of information is impractical given the large scale of online data, which highlights the need for automated systems. This paper presents an approach for detecting fake news by combining Machine Learning (ML) algorithms with Natural Language Processing (NLP) techniques. The dataset is preprocessed through steps such as tokenization, stop-word elimination, lemmatization, and feature extraction using TF-IDF. Models including Logistic Regression, Nave Bayes, Random Forest, and Support Vector Machine (SVM) are trained and tested. Their effectiveness is assessed using accuracy, precision, recall, and F1-score. Experimental outcomes indicate that SVM and Logistic Regression deliver superior performance, demonstrating that ML integrated with NLP can serve as a reliable method for identifying fake news on digital platforms.
Copyright
Copyright © 2025 Badhmeshwar S. This is an open access article distributed under the Creative Commons Attribution License.
