A scoping review on the use of natural language processing in research on political polarization: trends and research prospects

Abstract

As part of the “text-as-data” movement, Natural Language Processing (NLP) provides a computational way to examine political polarization. We conducted a methodological scoping review of studies published since 2010 (n = 154) to clarify how NLP research has conceptualized and measured political polarization, and to characterize the degree of integration of the two different research paradigms that meet in this research area. We identified biases toward US context (59%), Twitter data (43%) and machine learning approach (33%). Research covers different layers of the political public sphere (politicians, experts, media, or the lay public), however, very few studies involved more than one layer. Results indicate that only a few studies made use of domain knowledge and a high proportion of the studies were not interdisciplinary. Those studies that made efforts to interpret the results demonstrated that the characteristics of political texts depend not only on the political position of their authors, but also on other often-overlooked factors. Ignoring these factors may lead to overly optimistic performance measures. Also, spurious results may be obtained when causal relations are inferred from textual data. Our paper provides arguments for the integration of explanatory and predictive modeling paradigms, and for a more interdisciplinary approach to polarization research.

Party Prediction for Twitter

“…Malicious actors, such as governments attempting to interfere in other countries' elections, are already known to spread misinformation and try to sway users to particular ideologies and voting patterns (Eady et al 2023). In addition, although exact mechanisms and the role of the platform are still debated, social media has been consistently linked to increasing partisan polarization (Németh 2022). Consequently, there is no security through obscurity in this domain.…”

The East Asian Mahāyāna Teaching of the One Mind and Its Implications in a Polarized World

“…The linguistic aspect of polarization is often referred to as "language polarization" (e.g., Demata 2016;Irwin 2016;Németh 2023). Language polarization takes on various forms, including hate speech, fake news, conspiracy theories, and buzzwords that are loaded with value judgments.…”

Polarización política y medios de comunicación, su impacto en la democracia y en la sociedad

“…No por su novedad, sino por su popularización que, además, evidencia cómo el marcado crecimiento en el uso de redes sociales está generando enormes cantidades de datos personales y colectivos que se emplean para tratar de influir a la ciudadanía (Cantini et al, 2022). Sin embargo, más allá de estos usos espurios, se localizan propuestas académicas para avanzar hacia unos enfoques interdisciplinares que permitan el uso de la inteligencia artificial para investigar y reducir los efectos de las diferentes formas de polarización (Németh, 2023).…”