{"title":"An Arabic Corpus for Covid-19 related Fake News","authors":"Djamila Mohdeb, Meriem Laifa, Miloud Naidja","doi":"10.1109/ICRAMI52622.2021.9585909","DOIUrl":null,"url":null,"abstract":"In 2020, we have witnessed a universal health crisis that affected the lives of many people around the world. Covid-19 outbreak has been accompanied with an unprecedented wave of misinformation shared on the web and social media leading to confusion and inappropriate public reactions. In this paper, we investigate the fake news spread in Arabic content during the pandemic crisis. We have collected a dataset for the aim of detecting fake news that are related to the coronavirus subject. The dataset includes Arabic fake and true news extracted from reliable sources. To the best of our knowledge, it is the first fake news dataset on Covid-19 Arabic misinformation. The collected data have been explored then exploited for fake news detection task using the classification baseline methods. Results indicated comparable high performance of baseline models with a relative superiority of SVM classifier.","PeriodicalId":440750,"journal":{"name":"2021 International Conference on Recent Advances in Mathematics and Informatics (ICRAMI)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 International Conference on Recent Advances in Mathematics and Informatics (ICRAMI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICRAMI52622.2021.9585909","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 6
Abstract
In 2020, we have witnessed a universal health crisis that affected the lives of many people around the world. Covid-19 outbreak has been accompanied with an unprecedented wave of misinformation shared on the web and social media leading to confusion and inappropriate public reactions. In this paper, we investigate the fake news spread in Arabic content during the pandemic crisis. We have collected a dataset for the aim of detecting fake news that are related to the coronavirus subject. The dataset includes Arabic fake and true news extracted from reliable sources. To the best of our knowledge, it is the first fake news dataset on Covid-19 Arabic misinformation. The collected data have been explored then exploited for fake news detection task using the classification baseline methods. Results indicated comparable high performance of baseline models with a relative superiority of SVM classifier.