Table 6.

The features and datasets used in the news content-based approaches

Feature and metadata	Datasets	Reference
The average number of words in sentences, number of stop words, the sentiment rate of the news measured through the difference between the number of positive and negative words in the article	Getting real about fake news${}^{\text{a}}$, Gathering mediabiasfactcheck${}^{\text{b}}$, KaiDMML FakeNewsNet${}^{\text{c}}$, Real news for Oct-Dec 2016${}^{\text{d}}$	Kapusta et al. (2019)
The length distribution of the title, body and label of the article	News trends, Kaggle, Reuters	Kaur et al. (2020)
Sociolinguistic, historical, cultural, ideological and syntactical features attached to particular words, phrases and syntactical constructions	FakeNewsNet	Vereshchaka et al. (2020)
Term frequency	BuzzFeed political news, Random political news, ISOT fake news	Ozbay and Alatas (2020)
The statement, speaker, context, label, justification	POLITIFACT, LIAR${}^{\text{e}}$	Wang (2017)
Spatial vicinity of each word, spatial/contextual relations between terms, and latent relations between terms and articles	Kaggle fake news dataset${}^{\text{f}}$	Hosseinimotlagh and Papalexakis (2018)
Word length, the count of words in a tweeted statement	Twitter dataset, Chile earthquake 2010 datasets	Abdullah-All-Tanvir et al. (2019)
The number of words that express negative emotions	Twitter dataset	Abdullah-All-Tanvir et al. (2020)
Labeled data	BuzzFeed${}^{\text{g}}$, PolitiFact${}^{\text{h}}$	Mahabub (2020)
The relationship between the news article headline and article body. The biases of a written news article	Kaggle: real_or_fake${}^{\text{i}}$, Fake news detection${}^{\text{j}}$	Bahad et al. (2019)
Historical data. The topic and sentiment associated with content textual. The subject and context of the text, semantic knowledge of the content	Facebook dataset	Del Vicario et al. (2019)
The veracity of image text. The credibility of the top 15 Google search results related to the image text	Google images, the Onion, Kaggle	Vishwakarma et al. (2019)
Topic modeling of text and the associated image of the online news	Twitter dataset${}^{\text{k}}$, Weibo${}^{\text{l}}$	Amri et al. (2022)

${}^{\text{a}}$ https://www.kaggle.com/anthonyc1/gathering-real-news-for-oct-dec-2016, last access date: 26-12-2022

${}^{\text{b}}$ https://mediabiasfactcheck.com/, last access date: 26-12-2022

${}^{\text{c}}$ https://github.com/KaiDMML/FakeNewsNet, last access date: 26-12-2022

${}^{\text{d}}$ https://www.kaggle.com/anthonyc1/gathering-real-news-for-oct-dec-2016, last access date: 26-12-2022

${}^{\text{e}}$ https://www.cs.ucsb.edu/~william/data/liar_dataset.zip, last access date: 26-12-2022

${}^{\text{f}}$ https://www.kaggle.com/mrisdal/fake-news, last access date: 26-12-2022

${}^{\text{g}}$ https://github.com/BuzzFeedNews/2016-10-facebook-fact-check, last access date: 26-12-2022

${}^{\text{h}}$ https://www.politifact.com/subjects/fake-news/, last access date: 26-12-2022

${}^{\text{i}}$ https://www.kaggle.com/rchitic17/real-or-fake, last access date: 26-12-2022

${}^{\text{j}}$ https://www.kaggle.com/jruvika/fake-news-detection, last access date: 26-12-2022

${}^{\text{k}}$ https://github.com/MKLab-ITI/image-verification-corpus, last access date: 26-12-2022

${}^{\text{l}}$ https://drive.google.com/file/d/14VQ7EWPiFeGzxp3XC2DeEHi-BEisDINn/view, last access date: 26-12-2022