A Comprehensive Review on Fake News Detection with Deep and Machine Learning

EasyChair Preprint 13233

Abstract

Businesses in a wide range of sectors are stymied in their attempts to develop reliable methods for identifying online fake news. It can be challenging to tell the difference between legitimate content and the fake stuff that's out there on the internet because the fake stuff is usually written to trick people. In comparison to other mechanism education procedures, bottomless learning is better at detecting fake news. Complexity was cited as a reason why profound education methods for identifying fake news were overlooked in prior reviews. Devotion, Multiplicative Combative Links, and Bidirectional Encoder Demonstrations for Modifiers are all examples of deep learning algorithms that were left out of previous studies. This education goal to critically examine state-of-the-art methods for identifying fake news. We will begin by discussing the consequences of spreading misinformation. Then, we'll go over the NLP techniques and datasets that have been used in previous research. In order to classify typical procedures, it has been exposed to an exhaustive survey of bottomless learning-based approaches. Metrics for identifying sham broadcast are also discussed.

Keyphrases: Bottomless knowledge, Mechanism knowledge, fake news, machine learning

@booklet{EasyChair:13233,
  author    = {Mickey Sahu and Harsh Lohiya},
  title     = {A Comprehensive Review on Fake News Detection with Deep and Machine Learning},
  howpublished = {EasyChair Preprint 13233},
  year      = {EasyChair, 2024}}