Tracking causal relations in the news: data, tools, and models for the analysis of argumentative statements in online media

Abstract

Online debates and debate spheres challenge our assumptions about democracy, politics, journalism, trust, and truth in ways that make them a necessary object of study. In the present article, we argue that the study of online arguments can benefit from an interdisciplinary approach that combines computational methods for text analysis with conceptual models of opinion dynamics. The article thereby seeks to make a conceptual and methodological contribution to the field by highlighting the role of domain-crossing causal statements in debates of societal interest, and by providing a method for automatically mining such statements from textual corpora on the web. The article illustrates the relevance of this approach for the study of online debates by means of a case study in which we analyse cross-cutting statements on climate change and energy technologies from the comment section of the online newspaper The Guardian. In support of this case study, we use data and methods that are made openly available through the Penelope ecosystem of tools and techniques for computational social science.

Validating Argument-Based Opinion Dynamics with Survey Experiments

“…This kind of opinion alignment is a robust empirical fact, for instance, political dimensions such as "left" versus "right" are only meaningful only because of specific patterns of attitudinal correlations (Laver & Budge 1992;Laver 2014;. Also for this model attempts to derive realistic argument-opinion relations from textual data have been made (Willaert et al 2022). In this paper, we focus on a single-issue model with the aim to link micro-level assumptions about argument uptake to data from a survey experiment.…”