Text Analysis and Spatial Data for Economists
Over the past years, the availability of new data through the digitalization of legal, political, journalistic corpora, as well as the release of fine-grained spatial data, has allowed researchers to answer new research questions and to explore novel causal inference techniques.
The aim of this course is to introduce students to the quantitative analysis of textual data and to the use of spatial datasets. We will cover both applications in the recent empirical research and the implementation of text and spatial data analysis techniques through hands-on experiences using the R statistical programming language.
The course will cover – among others – the following topics:
- Web Scraping and automating collection of online data, including social media data
- Machine learning and text analysis
- Topic models
- Geographical data
- Spatial operations on vector objects
- Raster data
The course is organized around topics. Each topic is illustrated through the discussion of recent applications from applied research in economics. Students practice the theoretical concepts and the programming language with in-class exercises.
Students should bring a laptop with R and RStudio installed to all classes.
The final grade is composed of homework, in-class presentations (40%) and a project due at the end of the semester (60%).
There is no textbook for this course. All slides and sample programs will be published online. Additional resources will be discussed during the semester.