Menu
Menu
Install this application on your home screen for quick and easy access when you’re on the go.
Just tap then “Add to Home Screen”
Member rate 2,713.79 zł
Non-Member rate 5,427.58 zł
Save 221.03 zł Loyalty discount applied automatically*
Save 5% on each additional course booked
* If you attended a qualifying previous Methods School in 2025 or 2026, you qualify for 221.03 zł off your course fee.
Jagiellonian University: 8 – 11 September
Online: 14 – 15 September
Large Language Models (LLMs) are reshaping the methodological toolkit of contemporary social science. This course provides an accessible introduction to LLMs for researchers in sociology, political science, and related disciplines who wish to incorporate these tools into their research workflows.
The course is organised around four main components. It introduces the basic concepts behind LLMs, including how they are trained, how they generate language, and how they differ from earlier computational text‑analysis approaches. It then explores recent applications in the social sciences, such as automated content coding, large‑scale text analysis, survey augmentation, and experimental design.
You will work through guided demonstrations using simple coding environments with exercises covering prompt‑based classification, document summarisation, semantic search, and basic data extraction.
The course also addresses validation, bias, and responsible use, and discusses how LLMs can be integrated into research workflows.
Giovanni Pagano is a Research Fellow in the Department of Social and Political Sciences at the University of Milan. His research centres on political communication, party competition, and computational methods in political science, with a focus on the analysis of texts, visuals, and social media data.
Giovanni's work has appeared in journals including European Union Politics, Regulation & Governance, and Journal of Information Technology & Politics. He teaches courses and workshops on quantitative methods and computational approaches for social scientists.
This course introduces Large Language Models (LLMs) as emerging tools for social and political research. It combines conceptual discussion, examples from recent studies, and practical demonstrations to show how LLMs can be used in empirical research.
The course is organised around four core components: methodological foundations, applications in social science, practical workflows with real use cases, and key considerations such as validation, bias, and the limits of model‑based inference.
It begins by covering the basic principles of LLMs and situating them within computational text analysis. You will learn how these models are trained, how they differ from earlier approaches such as bag‑of‑words, topic models, and supervised classifiers, and key concepts including embeddings, transformer architecture, and training data.
It then explores current applications in social‑science research, such as automated analysis of political speech and media, prompt‑based classification of policy positions, survey data augmentation, pilot testing of experiments, and model‑based agents for studying collective dynamics.
The course then moves to guided Python demonstrations in notebook environments, covering tasks such as text classification, semantic search, survey‑question generation, and automated coding of qualitative material. The focus is on research workflows and methodological choices rather than advanced programming.
Finally, the course addresses validation, potential biases, and responsible and ethical use of LLMs, and considers how they can be integrated into various stages of the research workflow.
Introduction to LLMs and their place in computational social science; key concepts and comparison with earlier text‑analysis approaches.
Applications in social and political research, including case studies and research‑design discussion.
Practical demonstrations using Python notebooks to illustrate real research workflows.
Methodological considerations: validation, reproducibility, bias, and the limits of model‑based inference.
Integration into research workflows. You will discuss potential applications to your own research and reflect on methodological choices.
The course is structured into five live sessions, each lasting three hours. The first three sessions will take place from Tuesday 8 – Thursday 10 September at Jagiellonian University in Kraków. The remaining two sessions will take place on Monday 14 and Tuesday 15 September, online. You must attend all sessions to complete the course.
The instructor will also conduct Q&A sessions and offer designated office hours for one-to-one consultations.
You are expected to have a general understanding of social science research design and some familiarity with empirical research methods. No advanced programming skills are necessary. However, some familiarity with data‑analysis tools or scripting environments (such as R or Python) will make it easier for you to follow the hands‑on demonstrations.
This is an intermediate‑level course designed for PhD students, postdoctoral researchers, and social scientists interested in understanding how Large Language Models can be used in social and political research. The focus is on conceptual foundations, methodological applications, and practical demonstrations rather than advanced technical implementation.
You should have access to a laptop during the course sessions. Basic familiarity with working in notebook-based environments or running simple scripts will be helpful for engaging with the practical exercises. Instructions and example code will be provided.
You should expect approximately 24 hours of total engagement, including:
You will engage in a variety of activities designed to deepen your understanding of the subject matter. While daily live teaching sessions from the core of your learning experience, the learning commitment will extend beyond these. This ensures that you engage deeply with the course material, participate actively, and complete assessments to solidify your learning.
If you have registered and paid for the course, you will be given access to our Learning Management System (LMS) approximately two weeks before the course start date. Here, you can access course materials such as pre-course readings.
During the course week, participants are expected to commit time to preparing for each session, including readings and practical assignments.
This course description may be subject to subsequent adaptations (e.g. taking into account new developments in the field, participant demands, group size, etc.). Registered participants will be informed at the time of change.
By registering for this course, you confirm that you possess the knowledge required to follow it. The instructor will not teach these prerequisite items. If in doubt, please contact us before registering.