Suspicious News Detection Using Micro Blog Text

Suspicious News Detection Using Micro Blog Text Tsubasa Tagami1，Hiroki Ouchi2，Hiroki Asano3，Kazuaki Hanawa4 Kaori Uchiyama5，Kaito Suzuki6，Kentaro Inui7，Atsushi Komiya8 Atsuo Fujimura9，Hitofumi Yanai10，Ryo Yamashita11，Akinori Machino12 1,2,3,4,5,6,7Tohoku University，2,3,7RIKEN，8,9SmartNews, Inc.，10FactCheck Initiative Japan 11Watchdog for Accuracy inNews-reporting, Japan，12Hi-Ether Japan {1tagami，3asano，4hanawa，7inui}@ecei.tohoku.ac.jp，2hiroki.ouchi@riken.jp {5kaori.uchiyama.r1，6kaito.suzuki.p3}@dc.tohoku.ac.jp {8atsushi.komiya，9atsuo.fujimura}@smartnews.com 10yanai@fij.info，11rymst@gohoo.org，12akinori.machino@hi-ether.org Abstract We present a new task, suspicious news de- tection using micro blog text. This task aims to support human experts to detect suspicious news articles to be verified, which is costly but a crucial step before verifying the truthfulness of the articles. Specifically, in this task, given a set of posts on SNS referring to a news ar- ticle, the goal is to judge whether the article is suspicious or not. For this task, we create a publicly available dataset in Japanese and pro- vide benchmark results by using several ba- sic machine learning techniques. Experimen- tal results show that our models can reduce the cost of manual fact-checking process. 1 Introduction Fake news is a news article that is intentionally false and could mislead readers (Shu et al., 2017). The spread of fake news has a negative impact on our society and the news industry. For this reason, fake news detection and fact-checking are getting more attention. Problematic Issue. One problematic issue of fake news detection is that human fact-checking experts cannot keep up with the amount of misinforma- tion generated every day. Fact-checking requires advanced research techniques and is intellectually demanding. It takes about one day to fact-check a typical article and write a report to persuade readers whether it was true, false or somewhere in between (Hassan et al., 2015). Existing Approach. As a solution to the problem, various techniques and computational models for automatic fact-checking or fake news detection have been proposed (Vlachos and Riedel, 2014; Wang, 2017; Hanselowski et al., 2018). However, in practice, current computational models for automatic fake news detection cannot be used yet now due to the performance limitation. Thus, at the present, manual or partially automatic verification is a practical solution. Our Approach. To mitigate the problem, we aim to automate suspicious news detection. Specifically, we develop computational models for detecting sus- picious news articles to be verified by human ex- perts. We assume human-machine hybrid systems, in which suspicious articles are detected and sent to human experts and they verify the articles. Our motivation of this approach is to remedy the time-consuming step to find articles to check. Journalists have to spend hours going through a variety of investigations to identify claims (or articles) they will verify (Hassan et al., 2015). By automatically detecting suspicious articles, we can expect to reduce the manual cost. Our Task. We formalize suspicious news detec- tion as a task. Specifically, in this task, given a set of posts on SNS that refer to a news article, the goal is to judge whether the article is suspicious or not. The reason of using posts on SNS is that some of them cast suspicion on the article and can be regarded as useful and reasonable resources for suspicious …

Content truncated to 500 words