Our prototype web app, the Hansard Viewer , explores how the tools to measure lexican change – and more sophisticated NLP strategies such as parsing and measuring grammatical relationships – can open a window into political discourse that will make what happens in Parliament more transparent to researchers and everyday citizens alike.
For seven years, our lab, Democracy Lab, has been operating at the juncture of political, historical, and textual analysis of democratic debates, publishing numerous articles, collaborating with the builders of infrastructure to make text mining accessible to the public, and building a preliminary series of public-facing apps.
Users of the web application are able to use an array of data-mining and statistical approaches which can provide new insights into the evolution and nature of political language as it occurs in different time periods and in different contexts.
For our final app, citizens using our toolset will be able to easily navigate from an overview showing change over time, to a dramatization of how different candidates talk about the same issue, to the in-text mentions of word use that a computer has used to produce the visualizations in question.
Note:
Our app is currently under development. We appreciate your understanding as we resolve visual glitches and optimize performance. We have a known bug where the individual nations on the nation pairs page were counted too many times.
This work was supported in part by National Science Foundation (NSF) Grant (no. 1520103).
