Zoom Out and Observe: News Environment Perception for Fake News Detection

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics Volume 1: Long Papers, pages 4543 - 4556 May 22-27, 2022 c⃝2022 Association for Computational Linguistics Zoom Out and Observe: News Environment Perception for Fake News Detection Qiang Sheng, Juan Cao∗, Xueyao Zhang, Rundong Li, Danding Wang, Yongchun Zhu Key Lab of Intelligent Information Processing of Chinese Academy of Sciences, Institute of Computing Technology, Chinese Academy of Sciences University of Chinese Academy of Sciences {shengqiang18z,caojuan,zhangxueyao19s}@ict.ac.cn {lirundong20s,wangdanding,zhuyongchun18s}@ict.ac.cn Abstract Fake news detection is crucial for preventing the dissemination of misinformation on social media. To differentiate fake news from real ones, existing methods observe the language patterns of the news post and “zoom in” to ver- ify its content with knowledge sources or check its readers’ replies. However, these methods neglect the information in the external news environment where a fake news post is created and disseminated. The news environment rep- resents recent mainstream media opinion and public attention, which is an important inspira- tion of fake news fabrication because fake news is often designed to ride the wave of popular events and catch public attention with unex- pected novel content for greater exposure and spread. To capture the environmental signals of news posts, we “zoom out” to observe the news environment and propose the News Environ- ment Perception Framework (NEP). For each post, we construct its macro and micro news en- vironment from recent mainstream news. Then we design a popularity-oriented and a novelty- oriented module to perceive useful signals and further assist final prediction. Experiments on our newly built datasets show that the NEP can efficiently improve the performance of basic fake news detectors.1 1 Introduction The wide spread of fake news on online social media has influenced public trust (Knight Foun- dation, 2018) and poses real-world threats on pol- itics (Fisher et al., 2016), finance (ElBoghdady, 2013), public health (Naeem and Bhatti, 2020), etc. Under such severe circumstances, automatically detecting fake news has been an important counter- measure in practice. Besides directly observing the post’s content pat- terns (Volkova et al., 2017; Wang et al., 2018) (Fig- ∗Corresponding author. 1https://github.com/ICTMCG/ News-Environment-Perception/ Figure 1: Existing methods for fake news detection rely on (a) the post content itself and (b) related post- level signals like social context and knowledge. Unlike (a) and (b), our method captures (c) signals from news environments. ure 1(a)), most existing methods for fake news detection “zoom in” for finding richer post-level signal by checking user replies to the post (Shu et al., 2019a; Zhang et al., 2021) and verifying the claim with knowledge sources (Popat et al., 2018; Wang et al., 2020) (Figure 1(b)). However, these methods neglect a different line of “zooming out” to observe the external news environment where a fake news post is created and disseminated. Our starting point is that a news environment, which represents recent mainstream media opinion and public attention, is an important inspiration of the fabrication of contemporary fake news. Since any gains of fake news achieve only …

Content truncated to 500 words