Text Data in Economics Masterclass
Text Data in Economics Masterclass
QAPECLink opens in a new window in collaboration with PEPELink opens in a new window Research Group is offering a training opportunity to acquire important skills in text data analysis. The masterclass is intended for MRes-PhD students, staff of the Department and QAPEC and PEPE affiliates.
Prof Elliott AshLink opens in a new window, from ETC Zurich, will deliver the course. Elliott's research and teaching focus on empirical analysis of the law and legal system using techniques from econometrics, natural language processing, and machine learning.
Book Your Place
Prerequisites
Knowledge of Python basics. Supplementary materials will be provided prior to the course for those who need to learn Python (coming soon)
Learning Objectives
1. To implement and evaluate text-as-data methods.
2. To evaluate the use of text-analysis tools in economics research.
3. To plan a research project using text data.
Teaching Team
Instructor: Elliott AshLink opens in a new window, ashe@ethz.ch
TA: Claudia Marangon, claudia.marangon@gess.ethz.ch
Schedule
Lectures: 2 (1.5 hours) lectures per week for 4 weeks on Zoom from mid June to mid July 2022
TA office hrs: TBC
Syllabus
Course Format
- 10 lectures on zoom (10 hours), recorded
- 4 TA sessions on zoom (4 hours), recorded
- In-person workshopping of student project papers
Assignments
- 3 problem sets based on the example notebooks
- In-class presentation of a course reading, with a partner (sign up sheetLink opens in a new window)
- Referee report on one of the course readings
- Research proposal on a text-data project (first and second draft, individually or partners)
Critical Presentations
- Done in pairs
- 10 minutes maximum
- Present and critique the following:
- research question
- text-analysis method
- empirical methods
- results
- contribution
Lecture Schedule
June 15th | 13h UK | Lecture 1 |
June 17th | 10h | Lecture 2 |
June 20th | 10h | Lecture 3 |
June 22nd | 10h | Lecture 4 |
June 29th | 15h | Lecture 5 |
July 4th | 10h | Lecture 6 |
July 6th | 10h | Lecture 7 |
July 8th | 10h | Lecture 8 |
July 11th | 10h | Lecture 9 |
July 12th | 10h | Lecture 10 |
TA Session Schedule
June 16th | TBD | TA Session 1 |
June 21st | TBD | TA Session 2 |
July 5th | TBD | TA Session 3 |
July 13th | TBD | TA Session 4 |
Topics Outline and Main Economics Papers Readings
Sign-up sheet for discussant presentationsLink opens in a new window
1. Overview
a. Gentzkow, Kelly, and Taddy, “Text as DataLink opens in a new window.”
2. Style Features and Dictionaries
a. Enke (2020), Moral values and votingLink opens in a new window
b. Michalopoulous and Xue (2021), FolkloreLink opens in a new window
3. Tokenization
a. Gentzkow and Shapiro (2010), What Drives Media Slant? Evidence from U.S. Daily NewspapersLink opens in a new window.
b. Hassan, Hollander, Van Lent, and Tahoun (2019), Firm-Level Political Risk: Measurement and EffectsLink opens in a new window
4. Document Distance
a. Kelly, Papanikolau, Seru, and Taddy, Measuring technological innovation over the very long runLink opens in a new window
b. Cage, Herve, and Viaud, The production of information in an online worldLink opens in a new window
5. Topic Models
a. Hansen, McMahon, and Prat, Transparency and deliberation with the FOMC: A computational linguistics approachLink opens in a new window.
b. Ash, Morelli, and Vannoni, “More laws, more growth? Evidence from U.S. statesLink opens in a new window”
6. Supervised Learning
a. Gentzkow, Shapiro, and Taddy (2019), Measuring group differences in high-dimensional choices: Method and application to Congressional SpeechLink opens in a new window
b. Widmer, Galletta, and Ash (2022), Media Slant is ContagiousLink opens in a new window
7. Word Embeddings
a. Ash, Chen, and Ornaghi (2022), “Gender attitudes in the judiciary: Evidence from U.S. Circuit CourtsLink opens in a new window”
b. Ash, Gennaro, Hangartner, and Stampi-Bombelli (2022), “Immigration and Social Distance: Evidence from Newspapers during the Age of Mass Migration”.
8. Syntactic and Semantic Parsing
a. Antoniak, Mimo, and Levy (2019), Narrative paths and negotiation of power in birth storiesLink opens in a new window
b. Ash, Gauthier, and Widmer (2022), Relatio: Text semantics capture political and economic narrativesLink opens in a new window
9. Additional Topics
a. Ash, Durante, Grebenschikova, and Schwarz (2022), Visual Representation and Stereotypes in News MediaLink opens in a new window.
Resources
Further helpful resources can be found at the following links:
Form Submission
Please complete the form below to express your interest in partaking in the masterclass.