A Real-Time System for Credibility on Twitter

Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pages 6166–6173 Marseille, 11–16 May 2020 c⃝ European Language Resources Association (ELRA), licensed under CC-BY-NC 6166 A Real-Time System for Credibility on Twitter Adrian Iftene1, Daniela Gîfu1,2, Andrei-Remus Miron1, Mihai-Ștefan Dudu1 Alexandru Ioan Cuza University of Iași, Faculty of Computer Science1, Romanian Academy – Iași branch, Institute of Computer Science2 General Berthelot, 16, Iaşi 700483, Romania1, Codrescu 2, Iași 700481, Romania2 {adiftene, daniela.gifu}@info.uaic.ro Abstract Nowadays, social media credibility is a pressing issue of each of us who are living in an altered online landscape. The speed of news diffusion is striking. Given the popularity of social networks, more and more users began posting pictures, information, and news about personal life. At the same time, they started to use all this information to get informed about what their friends do or what is happening in the world, many of them arousing much suspicion. The problem we are currently experiencing is that we do not currently have an automatic method of figuring out in real-time which news or which users are credible and which are not, what is false or what is true on the Internet. The goal of this is to analyze Twitter in real-time using neural networks in order to provide us key elements about both the credibility of tweets and users who posted them. Thus, we make a real-time heatmap using information gathered from users to create overall images of the areas from which this fake news comes. Keywords: neural networks, credibility, real-time, Twitter 1. Introduction In present, the risk of running into misinformation is not negligible, especially on Social Media. For this reason, mining the credibility of both user and message itself constitute nowadays a major problem (Gînsca et al., 2015). The speed of news diffusion is striking worldwide. Given the increasing popularity of social networks, sharing your life on the Internet has become a natural activity for most of the users. The news is read quickly, marked with opinions (see Facebook), retransmitted (retweet on Twitter, share on Facebook) without having to check many times whether they are true or false news (Atodiresei et al., 2018). Researchers have begun in recent years to address the issue of identifying fake news and their credibility on television and YouTube (Ciampaglia et al., 2015; Clark, 2009), Twitter ((El Ballouli et al., 2017; Cusmuliuc et al., 2018; Iftene et al., 2017; Castillo et al., 2011), (Chu et al., 2010), (Cook et al., 2013), (Iozzio, 2018), Facebook (Allcott, and Gentzkow, 2017), (Chen et al., 2015) even showing sites that train and help users who want to identify false news (TenQuestionsForFakeNews). There is still a lot of talk about the influence of Twitter on the US elections in 2016 (Bovet and Makse, 2019) and the fact that there is a lot of fake news on Twitter (Brummette et al., 2018). Below we will see the most used technologies in identifying false news, part of them presented in the paper (Conroy et al., …

Content truncated to 500 words