Identifying Morality Frames in Political Tweets using Relational Learning

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9939–9958 November 7–11, 2021. c⃝2021 Association for Computational Linguistics 9939 Identifying Morality Frames in Political Tweets using Relational Learning Shamik Roy, Maria Leonor Pacheco, Dan Goldwasser Department of Computer Science Purdue University West Lafayette, IN, USA {roy98, pachecog, dgoldwas}@purdue.edu Abstract Extracting moral sentiment from text is a vi- tal component in understanding public opin- ion, social movements, and policy decisions. The Moral Foundation Theory identifies five moral foundations, each associated with a posi- tive and negative polarity. However, moral sen- timent is often motivated by its targets, which can correspond to individuals or collective en- tities. In this paper, we introduce morality frames, a representation framework for orga- nizing moral attitudes directed at different en- tities, and come up with a novel and high- quality annotated dataset of tweets written by US politicians. Then, we propose a relational learning model to predict moral attitudes to- wards entities and moral foundations jointly. We do qualitative and quantitative evaluations, showing that moral sentiment towards entities differs highly across political ideologies. 1 Introduction Morality is a set of principles to distinguish be- tween right and wrong. Shared moral values form the social and cultural norms that unite social groups (Dehghani et al., 2016). Moral Foundations Theory (MFT) (Haidt and Joseph, 2004; Haidt and Graham, 2007) provides a theoretical framework for analyzing different expressions of moral val- ues. The theory suggests that there are at least five basic moral values, emerging from evolutionary, social, and cultural origins. These are referred to as Moral Foundations (MFs), each with a positive and a negative polarity, and include Care/Harm, Fairness/Cheating, Loyalty/Betrayal, Authority/- Subversion, and Purity/Degradation (Table 1 pro- vides details). Identifying MF in text is a relatively new challenge and past work has relied on lexical resources such as the Moral Foundation Dictio- nary (Graham et al., 2009; Fulgoni et al., 2016; Xie et al., 2019) and annotated data (Johnson and Goldwasser, 2018; Lin et al., 2018; Hoover et al., 2020). Social and political science studies have repeat- edly shown the correlation between ideological and political stances and moral foundation pref- erences (Graham et al., 2009; Wolsko et al., 2016; Amin et al., 2017). For example, Graham et al., 2009 captures the correlation between political ide- ology and moral foundation usage, showing that Liberals have a preference for Care/Harm and Fair- ness/Cheating while Conservatives use all five. Our main intuition in this paper is that even when differ- ent groups use the same MF, the moral sentiment would be directed towards different targets. To clar- ify, consider the following tweets discussing the Affordable Healthcare Act (ACA, Obamacare). [@SenThadCochran and I]CARING are working to protect [MS small businesses]CARE−F OR from more expensive [#Obamacare mandates]HARMING. [The ACA]CARING was a life saver for the more than [130 million Americans]CARE−F OR with a preexisting con- dition – including covid now. [Republicans]HARMING want to take us back to coverage denials. While both tweets use the Care/Harm MF, in the …

Content truncated to 500 words