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.<b>Paper Citation</b>Ludovic 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}}<b>Code (from the paper) Github repo</b>https://github.com/lrheault/partyembed<b>Dataset Citation</b>Gentzkow, 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

本数据集由Matthew Gentzkow、Jesse M. Shapiro与Matt Taddy于2018年汇编完成。本项目将数据与代码整合至同一文件夹，并修改了Rheualt与Cochrane的代码内的路径以适配本项目。本次部分复现工作将Rheault与Cochrane 2020年论文src文件夹中的模型创建脚本整合至单个Jupyter Notebook中，仅用于复现图2中的3幅绘图。本数据集采用ODC-BY 1.0开源许可，但许可下拉菜单中未提供该选项，故选用CC BY 4.0许可。<b>论文引用</b>Ludovic Rheault和Christopher Cochrane. 2020. 《议会语料库意识形态定位分析的词嵌入方法》, 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}}<b>论文配套代码GitHub仓库</b>https://github.com/lrheault/partyembed<b>数据集引用</b>Gentzkow, Matthew, Jesse M. Shapiro, and Matt Taddy. 《第43至114届美国国会国会记录：演讲解析与短语计数》, 加利福尼亚州帕洛阿尔托：斯坦福图书馆[发行方], 2018-01-16. https://data.stanford.edu/congress_text