A data science approach to 138 years of congressional speeches

Abstract

The availability of automatic data analysis tools and large databases have enabled new ways of studying language and communication that were not possible in the pre-information era. Here we apply a quantitative analysis to a large dataset of USA congressional speeches made over a period of 138 years. The analysis reveals that the readability index of congressional speeches increased consistently until the 96th congress, and then started to decline. Congressional speeches have also become more positive over time, and in general express more sentiments compared to speeches made in the 19th century or early 20th century. The analysis also shows statistically significant differences between Democratic and Republican congressional speeches.

Principle of Least Effort and Sentence Length in Public Speaking

“…The object of this research was to study the public speeches of politicians. Previously, this has beencarried out several times (see, e.g., [32][33][34]). However, the objectives of those studies were different from the objective of this work (readability and sentiment analysis, letter frequency distribution, etc.).…”

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

“…It is worth noting that in the case of the latter two, the studies were co-authored not only by computer scientist but by domain experts as well. Some examples show that if there are only computer scientists among the authors, the interpretation is often missing, and the research questions are rather technical [ 82 ]. And vice versa: if there are only social scientist co-authors, the methodology is fairly simple, although the paper is rich in content: the research questions are explained, the meta-variables are well-chosen, and the results are embedded in an existing scientific discourse [ 51 , 52 ].…”

Congressional Committees, Electoral Connections, and Legislative Speech

“…Studies have also analyzed the content of legislative speeches to derive information about the political positions of legislators (Proksch and Slapin 2010; Schwarz et al 2017), gender differences (Bäck et al 2019; Vallejo Vera and Gómez Vidal 2021), and variations across parties regarding word usage (Tucker et al 2020), among other matters. Although this literature has become more prominent in recent years, it remains relatively thin regarding theoretical expectations of speech participation across different policy topics.…”