Measuring and Explaining Political Sophistication through Textual Complexity

Abstract

Political scientists lack domain-specific measures for the purpose of measuring the sophistication of political communication. We systematically review the shortcomings of existing approaches, before developing a new and better method along with software tools to apply it. We use crowdsourcing to perform thousands of pairwise comparisons of text snippets and incorporate these results into a statistical model of sophistication. This includes previously excluded features such as parts of speech and a measure of word rarity derived from dynamic term frequencies in the Google Books data set. Our technique not only shows which features are appropriate to the political domain and how, but also provides a measure easily applied and rescaled to political texts in a way that facilitates probabilistic comparisons. We reanalyze the State of the Union corpus to demonstrate how conclusions differ when using our improved approach, including the ability to compare complexity as a function of covariates.

Figure 1

Comparing Our Rescaled Measure to the FRE of the Snippets

Figure 2

Probability That a State of the Union Address Is Easier to Understand Than a Fifth Grade Text Baseline, Compared to FRE Note: The points and associated vertical lines are probability estimates and 95% confidence intervals for our measure. The blue line is the loess fit of half the ratio of the FRE for the SOTU to the FRE of the fifth‐grade text corpus.

Figure 3

Probability That a Spoken SOTU Address Was Easier to Understand Than Its Written Counterpart Note: The lines represent the 95% confidence intervals from bootstrapping.