Presented By: Michigan Institute for Data Science
Modeling the Perceived Truthfulness of Public Statements on COVID-19: A New Model for Pairwise Comparisons of Objects with Multidimensional Latent Attributes
Qiushi Yu - Ph.D. student, Political Science and Kevin Quinn - Professor, Political Science
What is more important for how individuals perceive the truthfulness of statements about COVID-19: a) the objective truthfulness of the statements, or b) the partisanship of the individual and the partisanship of the people making the statements? To answer this question, we develop a novel model for pairwise comparisons data that allows for a richer structure of both the latent attributes of the objects being compared and rater-specific perceptual differences than standard models. We use the model to analyze survey data that we collected in the summer of 2020. This survey asked respondents to compare the truthfulness of pairs of statements about COVID-19. These statements were taken from the fact-checked statements on https://www.politifact.com. We thus have an independent measure of the truthfulness of each statement. We find that the actual truthfulness of a statement explains very little of the variability in individuals’ perceptions of truthfulness. Instead, we find that the partisanship of the speaker and the partisanship of the rater account for the majority of the variation in perceived truthfulness, with statements made by co-partisans being viewed as more truthful.
Related Links
Explore Similar Events
-
Loading Similar Events...
