The analysis of utterances with imperative forms in Hungarian health-related fake news
In the recent years the number of health-related fake news has increased especially during the COVID-19 pandemic causing serious harms. Therefore, detecting fake news and disinformation has become a crucial aim in the world (UN 2023). Fact checking and linguistic analysis are two ways of identifying fake news. The present research aims to contribute to the internationally growing field of linguistic analysis of disinformation (cf. Chen et al. 2015, Scott 2021) by investigating linguistic features of Hungarian health-related fake news.
Our underlying assumption is that there are significant differences between the language use of fake news and real news. We have assumed that one of these differences is the use of directives as a potential tool of putting pressure on the readers. This paper focuses on the analysis of utterances with imperative forms in Hungarian health-related news, since the most direct and strongest strategy of performing directives is the use of verbs with an imperative suffix. The hypothesis we tested was that fake news contains significantly more directives with imperative forms than real news due to a higher motivation of placing pressure on readers. Since there is no one-to-one correspondence between the imperative form and the directive function, a manual qualitative analysis was required on a corpus to check which imperative forms perform directives.
Our MedCollect corpus consists of 630 fake news (383,908 token) and 748 real news (388,212 token) on health issues. After a prior automatic morphological identification of imperative verbal forms, we carried out a pragmatic annotation using WebAnno annotation tool. The results supported our hypothesis, out of the 2664 imperative forms 1146 occurrences performed directive functions, 1000 in fake news and 146 in real news, consequently fake news contained significantly higher number of imperative forms with directive function. The findings may contribute to automated fake news detection.
References
Chen, Y. – Conroy, N. J. – Rubin, V. L. (2015). Misleading Online Content: Recognizing Clickbait as “False News”. Conference paper. http://dl.acm.org/citation.cfm?doid=2823465.2823467 (Accessed 10. 11. 2023).
Scott, K. (2021). You won’t believe what’s in this paper! Clickbait, relevance and the curiosity gap. Journal of Pragmatics 175, 53–66.
UN (2023). United Nations. Our Common Agenda Policy Brief 8. Information Integrity on Digital Platforms. June 2023. https://www.un.org/sites/un2.un.org/files/our-common-agenda-policy-brief-information-integrity-en.pdf