Skip to contents

Built-in example datasets

Source: R/data.R
ljmds_data.Rd

Three longitudinal binary datasets ship with the package as CSV files in inst/extdata. Each has column 1 = time and columns 2.. = 0/1 indicators. The first two are derived from text but contain no source text; the third is non-text and demonstrates that the methodology applies beyond text mining.

Details

  • peace_declaration.csv : 78 years (1947–2025, no 1950), 95 keyword indicators from the English Peace Declaration of Hiroshima.

  • inaugural.csv : 59 inaugural addresses (1789–2021), 106 keyword indicators derived from the corpus distributed with the quanteda R package.

  • eurovision.csv : 68 contest years (1956–2023), 52 country participation indicators in the Eurovision Song Contest. Source: Amsterdam Music Lab Mirovision dataset (MIT licence).

Loading

d <- ljmds.read.csv("peace_declaration")   # or "inaugural", "eurovision"

See also

ljmds.read.csv() to load the data, ljmds.pipeline() for the full analysis pipeline.