Human-machine interaction: A case study on fake news detection using a backtracking based on a cognitive system

Abstract

Although the Internet provides a variety of news, it also can give confusion caused by personal subjective thoughts such as personal TV, blogs, and unproven news. The unproven news is written in a subjective direction with added personal opinions rather than objective content, so readers may acquire knowledge with the wrong outlook. In addition, fake news is being produced and the problem of social polarization is becoming serious. In the end, it is necessary to detect the fake news, but it is not easy to distinguish the truth of published news because of the lack of fake news distinction time compared to the speed of information sharing on the Internet and the diversity and strong subjectivity of news. Therefore, in this paper, the possibility of fake news is defined by using the reverse-tracking method of the articles which are posted on the Cognitive System. Finally, as the result, the detection rate is average 85%.

Introduction

In 2016, the Oxford Dictionary selected ‘post-truth’ as the word of the year. In recent years, the issue of fake News has attracted a great deal of attention in the world through the US presidential election and Brexit, which is the political goal of individuals, parties, and organizations in the sense that the UK withdraws from the European Union. The New York Times reported that Cameron Harris made and distributed the fake news and earned $5000 for a short time, shared by six million people. Because of the nature of the Internet, the number of visits to celebrity sites is related to advertising revenue, so publishers constantly raise exciting false facts to increase the number of visitors (Contributors, 2018a, Ogiela and Ogiela, 2014). As fake news is read by more and more people, it is affecting many people who are interested in politics. Harris’ fake news can be spread out through social networks, or even searched through the Google search engine. More fake news is produced because visitors accessing the fake news website become an ad base. On the other hand, the fake news in Korea is more of a political dispute, rather than an income source from advertising. In other words, making fake news about a politician that they do not support helps reinforce their solidarity. In the case of Korea, during the political turmoil in the second half of 2016, there was social controversy due to the fake news, and broadcast stars suffered from the fake news (Sangaiah, Samuel, Li, Abdel-Basset, & Wang, 2018). There are penalties for the production and sharing of the fake news both at home and abroad, but it is impossible to completely prevent the production and spread of the fake news and it takes a lot of time to distinguish between them (Han, 2017). In the end, it is necessary to determine the truth of a posting considering the time of posting, the author’s relationship with other posts, the credibility of the author, and where they share it, but it is impossible for a person to handle it all. Therefore, a system that defines the reliability of the news is needed and the system should be able to grasp the surrounding situation and the characteristics of the news. This study suggests a cognitive system applying backtracking to judge false news based on the characteristics of web posting (Contributors, 2018c). To date, the characteristics of the fake news are that people with malicious intent post the fake news and others following the malice share the news (Contributors, 2018b). Reverse-Tracking on the fake news can reveal features that focus on a certain few users, rather than passing similar news from a variety of sources (Ogiela, 2008, Pang and Goodwin, 2003). If it were a normal issue article, similar posts would have been found in various places. According to this research, the provider of the news posted in the place as the personal blog is backtracked. Through such a process, we identify the characteristics of the first published place (such as newspaper, bureau, freelance journalist, etc.). At the same time, we understand the diversity of sites that have published the topic. Through such a combination of methods, the possibility of false news is determined. In other words, we propose cognitive system based on backtracking. The composition of this study is as follows. Chapter 2 summarizes the related research that defines fake news and cognitive system, and chapter 3 explains the proposed Fake News Detect System (FNDS) based on Reverse-Tracking with a cognitive system. Chapter 4 analyzes and summarizes the use cases using the proposed method, and chapter 5 concludes.