Motivation (i)
How do government and opposition parties differ in their sentiment in statements on the past, present, and future (Mueller, 2022)?
Motivation (ii)
How do autocracies adapt their political messaging during periods of leadership succession (Boussalis et al, 2023)?
Motivation (iii)
Under what conditions elites “overpraise” the ruler and imitate their rhetoric (Baturo et al, 2025)?
Text Analysis Assumptions
Texts represent an observable implication of some underlying characteristic of interest
- An attribute of the author
- A sentiment or emotion
- Salience of a political issue
Texts can be represented through extracting their features
- Most common is the bag of words assumption
- Many other possible definitions of “features” (e.g. word embeddings)
A document-feature matrix can be analyzed using quantitative methods to produce meaningful and valid estimates of the underlying characteristic of interest
Text Analysis Principles
- All quantitative models for textual analysis are wrong – but some are useful
- Quantitative methods for text amplify resources
- There is no globally best method for automated text analysis
- Validate, validate, validate (!!!)
This Workshop
is applied
- follow and execute the code
- do the exercises
- ask questions
focuses on “traditional” QTA methods
- we will cover AI only briefly
- otherwise, we have to have another class
Time to turn to practice