讲解Big Data、辅导RStudio留学生、讲解R程序语言、辅导R编程 辅导Python编程|调试Matlab程序

- 首页 >> 其他
Analyzing EU Politics with Big Data
Summer Semester 2019
Homework 1
Due: April 11, 12h00 (via Ilias)
1. If you have not done so yet, install the following programs on your laptop:
(a) R: http://www.r-project.org/
(b) RStudio: http://www.rstudio.com
(c) The R packages quanteda and quantedaData
(d) LATEX
on Windows: https://www.tug.org/protext/
on Mac: https://tug.org/mactex/
Complete the following assignment using R Markdown in RStudio. Create a new
R Markdown document in RStudio and select “Knit PDF” to produce a PDF
output file with your write up and the code output. More information on the
syntax is available here: http://rmarkdown.rstudio.com/.
2. Using R Markdown, on one page (maximum!), draft a proposal for a quantitative text
analysis project related to the analysis of EU politics. Your proposal should contain
the following information a) a research question of the project, b) the quantity of
interest (variable) your are trying to estimate from text and its relation to the project
(independent variable? dependent variable?), c) the potential text sources and their
electronic availability, d) mentioning of a QTA method described in Grimmer and
Stewart (2013) or Slapin and Proksch (2014) that you think is best suited to estimate
the quantity of interest.
3. Use the UK House of Commons Brexit debate corpus from class. This is the debate
that took place on April 2, 2019.
(a) Subset this corpus to speeches on the withdrawal from the EU motion, but keep
all speakers.
(b) Which MPs talk about a no deal brexit, which MPs talk about a public vote?
Construct a corresponding dictionary and use the dfm() function on the subsetted
corpus and apply the dictionary option within the function. Use ?dfm() to find
out how to apply a dictionary. Summarize your analysis in a brief paragraph.