Partial replication of a study by Ludovic Rheault and Christopher Cochrane (2020) on word embeddings for the analysis of ideological placement in US parliamentary speeches.

The dataset was collated by Matthew Gentzkow, Jesse M. Shapiro and Matt Taddy (2018). The project combines the data and code into one folder, and alters paths within Rheault and Cochrane's code to incorporate this. The partial replication incorporates model creation scripts from the src folder of the Rheualt and Cochrane (2020) paper into a single Jupyter Notebook exclusively for recreating the 3 plots in Figure 2.The dataset is available under the ODC-BY 1.0 license, however this was unavailable in the license dropdown, so CC BY 4.0 was selected.Paper CitationLudovic Rheault and Christopher Cochrane. 2020. Word Embeddings for the Analysis of Ideological Placement in Parliamentary Corpora. Political Analysis 28(1): 112-133.@article{RHE20,author = {Ludovic Rheault and Christopher Cochrane},title = {Word Embeddings for the Analysis of Ideological Placement in Parliamentary Corpora},journal = {Political Analysis},year = {2020},volume = {28},number = {1},pages = {112-133}}Code (from the paper) Github repohttps://github.com/lrheault/partyembedDataset CitationGentzkow, Matthew, Jesse M. Shapiro, and Matt Taddy. Congressional Record for the 43rd-114th Congresses: Parsed Speeches and Phrase Counts. Palo Alto, CA: Stanford Libraries [distributor], 2018-01-16. https://data.stanford.edu/congress_text