Modeling Framing in Immigration Discourse on Social Media

Abstract

The framing of political issues can influence policy and public opinion. Even though the public plays a key role in creating and spreading frames, little is known about how ordinary people on social media frame political issues. By creating a new dataset of immigrationrelated tweets labeled for multiple framing typologies from political communication theory, we develop supervised models to detect frames. We demonstrate how users' ideology and region impact framing choices, and how a message's framing influences audience responses. We find that the more commonlyused issue-generic frames obscure important ideological and regional patterns that are only revealed by immigration-specific frames. Furthermore, frames oriented towards human interests, culture, and politics are associated with higher user engagement. This large-scale analysis of a complex social and linguistic phenomenon contributes to both NLP and social science research. Frame Type Frame Description Issue-Generic Economic Financial implications of an issue Policy Capacity & Resources The availability or lack of time, physical, human, or financial resources Morality & Ethics Perspectives compelled by religion or secular sense of ethics or social responsibility Fairness & Equality The (in)equality with which laws, punishments, rewards, resources are distributed Legality, Constitutionality & Jurisdiction Court cases and existing laws that regulate policies; constitutional interpretation; legal processes such as seeking asylum or obtaining citizenship; jurisdiction

To Protect and To Serve? Analyzing Entity-Centric Framing of Police Violence

“…Furthermore, it is grounded heavy in the social science literature. Similar methods could be applied to other major issues such as climate change (Luo et al, 2020a) and immigration (Mendelsohn et al, 2021), where entities include politicians, protesters, and minorities, and where race, mental illness, and unarmed status may all be salient framing devices (e.g. describing the perpetrator or victim of anti-Asian abuse or violence; Gover et al 2020;Chiang 2020;Ziems et al 2020;Vidgen et al 2020).…”

“…Field et al (2018) built lexicons from the MFC annotations to classify issue frames in Russian news, and Roy and Goldwasser (2020) extended this work with subframe lexicons to refine the broad categories of the MFC. Some have considered the way Moral Foundations (Haidt and Graham, 2007) can serve as issue frames (Kwak et al, 2020;Mokhberian et al, 2020;Priniski et al, 2021), and others have built issue-specific typologies (Mendelsohn et al, 2021). While issue framing has been well-studied (Ajjour et al, 2019;Baumer et al, 2015), entity framing remains under-examined in NLP with a few exceptions.…”

“…As a case study, we consider news coverage of police violence. Though we choose this domain for the stark contrast between two readily-discernible entities (police and victim), our framing measures can also be applied to other major social issues (Luo et al, 2020b;Mendelsohn et al, 2021), and salient entities involved in these events, like protesters, politicians, migrants, etc.…”

Modeling Ideological Agenda Setting and Framing in Polarized Online Groups with Graph Neural Networks and Structured Sparsity

“…Previous NLP work has shown that agenda setting and framing are two key mechanisms by which attention can be drawn to certain topics (agenda setting) or certain aspects of a topic (framing) during political communication (Card et al, 2015;Tsur et al, 2015;Card et al, 2016;Field et al, 2018;Demszky et al, 2019;Mendelsohn et al, 2021). Here, we use agenda setting and framing to characterize differences between online discussion groups.…”

To Protect and To Serve? Analyzing Entity-Centric Framing of Police Violence

“…Field et al (2018) built lexicons from the MFC annotations to classify issue frames in Russian news, and Roy and Goldwasser (2020) extended this work with subframe lexicons to refine the broad categories of the MFC. Some have considered the way Moral Foundations (Haidt and Graham, 2007) can serve as issue frames (Kwak et al, 2020;Mokhberian et al, 2020;Priniski et al, 2021), and others have built issue-specific typologies (Mendelsohn et al, 2021). While issue framing has been well-studied (Ajjour et al, 2019;Baumer et al, 2015), entity framing remains under-examined in NLP with a few exceptions.…”