A systematic survey on deep learning and machine learning approaches of fake news detection in the pre- and post-COVID-19 pandemic

Abstract

PurposeThe rapid advancement of technology in online communication and fingertip access to the Internet has resulted in the expedited dissemination of fake news to engage a global audience at a low cost by news channels, freelance reporters and websites. Amid the coronavirus disease 2019 (COVID-19) pandemic, individuals are inflicted with these false and potentially harmful claims and stories, which may harm the vaccination process. Psychological studies reveal that the human ability to detect deception is only slightly better than chance; therefore, there is a growing need for serious consideration for developing automated strategies to combat fake news that traverses these platforms at an alarming rate. This paper systematically reviews the existing fake news detection technologies by exploring various machine learning and deep learning techniques pre- and post-pandemic, which has never been done before to the best of the authors’ knowledge.Design/methodology/approachThe detailed literature review on fake news detection is divided into three major parts. The authors searched papers no later than 2017 on fake news detection approaches on deep learning and machine learning. The papers were initially searched through the Google scholar platform, and they have been scrutinized for quality. The authors kept “Scopus” and “Web of Science” as quality indexing parameters. All research gaps and available databases, data pre-processing, feature extraction techniques and evaluation methods for current fake news detection technologies have been explored, illustrating them using tables, charts and trees.FindingsThe paper is dissected into two approaches, namely machine learning and deep learning, to present a better understanding and a clear objective. Next, the authors present a viewpoint on which approach is better and future research trends, issues and challenges for researchers, given the relevance and urgency of a detailed and thorough analysis of existing models. This paper also delves into fake new detection during COVID-19, and it can be inferred that research and modeling are shifting toward the use of ensemble approaches.Originality/valueThe study also identifies several novel automated web-based approaches used by researchers to assess the validity of pandemic news that have proven to be successful, although currently reported accuracy has not yet reached consistent levels in the real world.

Classification of Tweets Causing Deadlocks in Jakarta Streets with the Help of Algorithm C4.5

“…The C4.5 algorithm was employed in this work to categorize traffic congestion in DKI Jakarta, which is a data mining approach. The C4.5 method is a mechanism for converting all very big facts into decision trees [4]. The C4.5 method is deemed the best suitable for twitter data categorization since it achieves the maximum classification accuracy when compared to other algorithms such as Naive Bayes [5].…”

A Taxonomy of Fake News Classification Techniques: Survey and Implementation Aspects

“…Lack of proper review and information regarding future scope. Verma et al [28] Reviewed the existing fake news detection technologies by exploring various ML and DL techniques Systematically dissected fake news detection into two approaches, namely ML and DL, to present a better understanding and a clear objective. Also presented a viewpoint on which approach is better and future research trends, issues and challenges for researchers, given the relevance and urgency of a detailed and thorough analysis of existing models Timeline, impact and sources of fake news are missing.…”

Fake News Detection Techniques on Social Media: A Survey

“…The strategy did not intend to design efficient rumor management tactics after detecting a rumor at an early stage in its life. Additionally, Varma et al [31] discovered fraudulent postings in real-time Facebook data by developing a REST browser, which is a Facebook inspector. Accuracy, reaction time, accuracy, recall, and ROC AUC are all metrics that are used to evaluate the FBI's overall performance.…”

“…Others, such as convolutional neural networks (CNN) [45], might be used to represent postbased attributes to better capture people's thoughts and reactions to bogus news. According to the authors, photos in social media postings may also be used to better comprehend people's reactions to news events [20,31]. Network-based characteristics are retrieved and utilized to demonstrate the different processes by which various kinds of networks are built.…”

“…(i) Lexical characteristics, such as the total number of words, the number of characters in each word, the frequency of big words, and the number of unique terms (ii) Functional phrases, n-grams, and other syntactic properties such as a bag of words techniques [31], or punctuation and part of speech (POS) tagging. Additionally, visual signals are a critical modulator in the propagation of misleading news [29].…”