Abstract
AbstractIn today’s world, due to the emerging use of social media platforms, fake news spreads like a bonfire in the online world. Social media and various other news media broadcast fake news to increase viewership and readership among people to make the post trending. The people get easily attracted to fake news psychologically. In this paper, we have proposed a new fake news detection method with most frequent 1000 words in a corpus, consisting of the statements of an open freely accessible dataset named Liar (Wang in “Liar, liar pants on fire”: a new benchmark dataset for fake news detection, 2017 [18]). This paper also aims at studying different standard and basic techniques useful for text classification in the context of fake news detection. We have studied the performance of basic machine learning (ML) algorithms using basic lexicon-based features being implemented over standard fake news detection dataset “Liar” (Wang in “Liar, liar pants on fire”: a new benchmark dataset for fake news detection, 2017 [18]). We have also studied the effect of the feature–classifier combination for a Bengali fake news detection dataset, “BanFakeNews” (Hossain et al. in BanFakeNews: a dataset for detecting fake news in Bangla, 2020 [8]) as well.KeywordsFake news detectionText classificationText miningTFTF-IDFMachine learning
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
