12 Characterizing Documents
Readings
Text as Data in Economic Analysis by Tarek A. Hassan, Stephan Hollander, Aakash Kalyani, Laurence van Lent, Markus Schwedeler, and Ahmed Tahoun
Additional References (Not Required)
Measuring Economic Policy Uncertainty by Scott Baker, Nicholas Bloom, and Steven Davis
Measuring Technological Innovation over the Long Run by Bryan Kelly, Dimitris Papanikolaou, Amit Seru, and Matt Taddy
The Education-Innovation Gap by Barbara Biasi and Song Ma
Lecture
Lab
Lab 12 uses the same data set on NBER working papers from 2024 that we analyzed in Lab 11. In this lab, you will measure document distance in terms of both cosine similarity and Euclidean distance, and then use these measures to indentify similar papers and papers that are relatively unique. The template for the lab is available in R or Python.