Decision-making in politics is now more informed by data than ever before. Data analysis guides voter targeting by campaigns, predictions about election outcomes, and critical policy decisions made by government officials – to name just a few important areas touched by the revolution in the availability and use of data. This course covers key areas of politics transformed in recent years by data science, and it introduces fundamental tools of data science through applications to politics. Planned topics include campaigns and get out the vote, predicting election outcomes, redistricting and gerrymandering, and analyzing opinions expressed in social media and online discussion. The course takes a problem-driven approach, covering background and academic literature on each topic, learning a relevant data science tool or method, and then applying it to real-world data. A primary goal of the course is to give students an opportunity to develop data analysis skills relevant for working in politics, including writing and implementing code in statistical software packages; through applications students will gain experience with data wrangling/cleaning/formatting, record linkage, regression, prediction, visualization, unstructured data, and text analysis.
Suggested prerequisites: An understanding of intro-level statistics and probability theory (e.g., API-201).