A Holistic Framework for Analyzing the COVID-19 Vaccine Debate

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5821 - 5839 July 10-15, 2022 ©2022 Association for Computational Linguistics A Holistic Framework for Analyzing the COVID-19 Vaccine Debate Maria Leonor Pacheco1∗ Tunazzina Islam1∗ Monal Mahajan1 Andrey Shor1 Ming Yin1 Lyle Ungar2 Dan Goldwasser1 1CS, Purdue University, USA, 2CIS, University of Pennsylvania, USA {pachecog,islam32,mmahaja,ashor,mingyin,dgoldwas}@purdue.edu ungar@cis.upenn.edu Abstract The Covid-19 pandemic has led to infodemic of low quality information leading to poor health decisions. Combating the outcomes of this in- fodemic is not only a question of identifying false claims, but also reasoning about the de- cisions individuals make. In this work we pro- pose a holistic analysis framework connecting stance and reason analysis, and fine-grained en- tity level moral sentiment analysis. We study how to model the dependencies between the dif- ferent level of analysis and incorporate human insights into the learning process. Experiments show that our framework provides reliable pre- dictions even in the low-supervision settings. 1 Introduction One of the unfortunate side-effects of the Covid- 19 pandemic is a global infodemic flooding social media with low quality and polarizing informa- tion about the pandemic, influencing public percep- tion on it (Tagliabue et al., 2020). As studies have shown (Montagni et al., 2021), these influences have clear real-world implications, in terms of pub- lic acceptance of treatment options, vaccination and prevention measures. Most computational approaches tackling the Covid-19 infodemic view it a misinformation de- tection problem. In other words, they look at identi- fying false claims and analyzing reactions to them on social media (Hossain et al., 2020; Alam et al., 2021; Weinzierl et al., 2021). This approach, while definitely a necessary component in fighting the infodemic, does not provide policy makers and health-professionals with much needed informa- tion, characterizing the reasons and attitudes that underlie the health and well-being choices individ- uals make. Our goal in this paper is to suggest a holistic analysis framework, providing multiple inter- connected views of the opinions expressed in *Equal contribution Figure 1: Holistic Analysis Framework of Social Me- dia Posts, Connecting entity-level Moral Perspectives, Stance and Arguments Justifying it. text. We specifically focus on a timely topic, attitudes explaining vaccination hesitancy. Fig- ure 1 describes an example of our framework. Our analysis identifies the stance expressed in the post (anti-vaccination) and the rea- son for it (distrust of government). Given the ideologically polarized climate of social media discussion on this topic, we also aim to characterize the moral attitudes expressed in the text (oppression), and how different entities mentioned in it are perceived (“Biden, Government” are oppressing, “citizens, us” are oppressed). When constructing this framework we tackled three key challenges. 1. How should these analysis dimensions be operationalized? While stance prediction is an established NLP task, constructing the space of possible arguments justifying stances on a given topic, and their identification in text, are still open challenges. We take a human-in-the-loop approach to both problems. We begin by defining a seed …

Content truncated to 500 words