Workshop sobre LLMs y análisis de textos políticos

Encuentro metodológico sobre el uso de grandes modelos de lenguaje en ciencias sociales, con sesiones sobre anotación de textos, sesgos, medición del populismo, escalado de textos políticos y aplicaciones a la investigación comparada.

21 enero 2024
Barcelona
Large Language Models
9:00
Introducción
Xavier Fernández
9:45
LLMs for Text Annotation: Promises, Patterns and Pitfalls of a new Methodological Approach
Arnault Chatelain
10:30
Machine Bias. How much, and how, are LLMs biased? An Experiment.
Etienne Ollion
11:15-11:45
Pausa
11:45
Measuring Populism with Large Language Models: Prompt engineering as qualitative social science
Petter Törnberg
12:30
Scaling Political Texts with ChatGPT
Gaël Le Mens
13:15-14:30
Comida
Sesión paralela 1
14:30
Central Banking Under Pressure: A Textual Measure of Dominance and Coordination
Lauren Leek
15:15
Deep Active Learning for Data Mining from Conflict Text Corpora
Mihai Croicu
16:00
Coding Political Regimes with LLMs
Nils B. Weidmann
16:45
More Discretion, More Regulation? Examining Regulatory Production in the United Kingdom, 1991-2022
Nir Kosti
Sesión paralela 2
14:30
Party discipline and dyadic representation
Oda Nedregard
15:15
Holy Words, Contentious Politics: Discourse on Abortion Rights in Religious Sermons
Nela Mrchkovska
16:00
DOPEH - Dynamics of online political elite hostility: The audio-visual packaging of negative and uncivil campaign ads on Meta
Philipp Mendoza
16:45
Political Sycophancy of Large Language Models: Do they align with German voters?
Jan Batzner
17:30
Conferencia invitada
Fabrizio Gilardi