Text Analysis and Spatial Data for Economists
The course is divided into two parts:
Part I: spatial data
- Working with spatial data in R
- Geographical data
- Spatial operations on vector objects
- Raster (staellite) data
Part II: text analysis
- Working with text in Python
- Introduction to Spacy
- Web scraping and automating collection of online data, including social media data
- Basics of natural language processing
- Named entity recognition
- Text feature extraction, topic modelling, and text classification
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 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 to all classes.
The final grade is composed of homework (40%) and a project due at the end of the semester (60%).