"Advancements in Fake News Detection: A Comparative Study of Machine and Deep Learning Methods"

Abstract

In the contemporary landscape of information dissemination, the detection of fake news has emerged as a crucial undertaking due to the rapid proliferation of misinformation across various online channels. This study undertakes a comprehensive examination of fake news detection techniques, encompassing both traditional machine learning and advanced deep learning methods. We explore the efficacy of diverse feature extraction methods coupled with supervised learning methods. Through experiments conducted on established benchmark datasets, we assess the performance of these approaches in terms of classification report, while also scrutinizing their computational efficiency and scalability. Our findings offer valuable insights into the strengths and limitations of each method for fake news detection, thereby furnishing researchers and practitioners with guidance for formulating effective strategies to combat misinformation across online media platforms.