An Arabic Corpus of Fake News: Collection, Analysis and Classification

Alkhair, Maysoon; Meftouh, Karima; Smaïli, Kamel; Othman, Nouha

doi:10.1007/978-3-030-32959-4_21

Cited by 45 publications

(31 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e availability of Arabic FND datasets [33] and recent advancements in Arabic transformers and transformerbased approaches have encouraged the Arabic NLP community to further the development of Arabic Transformers, e.g., AraBERT [34], AraELECTRA [35], AraGPT2 [36], QARiB [37] Arbert, and Marbert [38].…”

Section: Methodsmentioning

confidence: 99%

Arabic Fake News Detection: Comparative Study of Neural Networks and Transformer‐Based Approaches

et al. 2021

View full text Add to dashboard Cite

Fake news detection (FND) involves predicting the likelihood that a particular news article (news report, editorial, expose, etc.) is intentionally deceptive. Arabic FND started to receive more attention in the last decade, and many detection approaches demonstrated some ability to detect fake news on multiple datasets. However, most existing approaches do not consider recent advances in natural language processing, i.e., the use of neural networks and transformers. This paper presents a comprehensive comparative study of neural network and transformer-based language models used for Arabic FND. We examine the use of neural networks and transformer-based language models for Arabic FND and show their performance compared to each other. We also conduct an extensive analysis of the possible reasons for the difference in performance results obtained by different approaches. The results demonstrate that transformer-based models outperform the neural network-based solutions, which led to an increase in the F1 score from 0.83 (best neural network-based model, GRU) to 0.95 (best transformer-based model, QARiB), and it boosted the accuracy by 16% compared to the best in neural network-based solutions. Finally, we highlight the main gaps in Arabic FND research and suggest future research directions.

show abstract

Section: Methodsmentioning

confidence: 99%

Arabic Fake News Detection: Comparative Study of Neural Networks and Transformer‐Based Approaches

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Two different feature extraction techniques and six machine learning algorithms were investigated and compared based on a dataset from political articles that were collected from Reuters.com and kaggle.com for real and fake news. Another Arabic corpus for the task of detecting fake news on YouTube is presented in [18]. The authors introduced a corpus that covered topics most concerned by rumors.…”

Section: Related Workmentioning

confidence: 99%

Fake News Detection in Arabic Tweets during the COVID-19 Pandemic

Mahlous¹,

Al-Laith²

2021

IJACSA

View full text Add to dashboard Cite

In March 2020, the World Health Organization declared the COVID-19 outbreak to be a pandemic. Soon afterwards, people began sharing millions of posts on social media without considering their reliability and truthfulness. While there has been extensive research on COVID-19 in the English language, there is a lack of research on the subject in Arabic. In this paper, we address the problem of detecting fake news surrounding COVID-19 in Arabic tweets. We collected more than seven million Arabic tweets related to the corona virus pandemic from January 2020 to August 2020 using the trending hashtags during the time of pandemic. We relied on two fact-checkers: the France-Press Agency and the Saudi Anti-Rumors Authority to extract a list of keywords related to the misinformation and fake news topics. A small corpus was extracted from the collected tweets and manually annotated into fake or genuine classes. We used a set of features extracted from tweet contents to train a set of machine learning classifiers. The manually annotated corpus was used as a baseline to build a system for automatically detecting fake news from Arabic text. Classification of the manually annotated dataset achieved an F1-score of 87.8% using Logistic Regression (LR) as a classifier with the n-gram-level Term Frequency-Inverse Document Frequency (TF-IDF) as a feature, and a 93.3% F1score on the automatically annotated dataset using the same classifier with count vector feature. The introduced system and datasets could help governments, decision-makers, and the public judge the credibility of information published on social media during the COVID-19 pandemic.

show abstract

“…Detection of Arabic fake news is considered a rough task as the Arabic sentiment resources are limited as well as the corpora and lexicon of Arabic language. Therefore, some researchers [6], [7], [8], [9], [12] and [13] have spent some time trying to solve these issues and implement fake news detection for Arabic texts. Alkhair et al [12] classified Arabic YouTube comments into rumor and not-rumor.…”

Section: A Arabic Fake News Detectionmentioning

confidence: 99%

Anti-Islamic Arabic Text Categorization using Text Mining and Sentiment Analysis Techniques

Alraddadi¹,

Ghembaza²

2021

IJACSA

View full text Add to dashboard Cite

The aim of this research is to detect and classify websites based on their content if it encourages spreading hate speech toward Islam and Muslims, or Islamophobia using sentiment analysis and web text mining techniques. In this research, a large dataset corpus has been collected, to identify and classify anti-Islamic online contents. Our target is to automatically detect the content of those websites that are hostile to Islam and transmitting extremist ideas against it. The main purpose is to reduce the spread of those webpages that give the wrong idea about Islam. The proper dataset is collected from different sources, and the two datasets for the Arabic language (balanced and unbalanced) have been produced. The framework of the proposed approach has been described. The approach used in this framework is based on supervised Machine Learning (ML) approach using Support Vector Machines (SVM) and Multinomial Naive Bayes (MNB) models as classifiers, and Term Frequency-Inverse Document Frequency (TF-IDF) as feature extraction. Different experiments including word level and trigram level on the two datasets have been conducted, and compared the obtained results. The experimental results shows that the supervised ML approach using word level is the finest approach for both datasets that produce high accuracy with 97% applied on the balanced Arabic dataset using SVM algorithm with TF-IDF as feature extraction. Finally, an interactive webapplication prototype has been developed and built in order to detect and classify toxic language such as anti-Islamic online textcontents.

show abstract

An Arabic Corpus of Fake News: Collection, Analysis and Classification

Cited by 45 publications

References 11 publications

Arabic Fake News Detection: Comparative Study of Neural Networks and Transformer‐Based Approaches

Arabic Fake News Detection: Comparative Study of Neural Networks and Transformer‐Based Approaches

Fake News Detection in Arabic Tweets during the COVID-19 Pandemic

Anti-Islamic Arabic Text Categorization using Text Mining and Sentiment Analysis Techniques

Contact Info

Product

Resources

About