Large Language Models for Social Data Analysis

The course aims to bring students, researchers and professionals interested in social data analysis up to speed with the technology of Large Language Models (LLMs).

Ziele und Nutzen

Course language

English

Course topic

Large Language Models (LLMs) are a powerful machine learning technique able to represent and generate text, as well as data in other modalities. LLMs can also be used for automating several data analysis tasks with little tuning. The course provides several applications using social data, that will be implemented in practical sessions.

The practical sessions will showcase examples of data analysis tasks using LLMs in a variety of novel ways. These include the large-scale detection of online media polarization, the thematic clustering and labeling of textual sources, and how to use LLMs for data cleaning and analysis.

Course objectives

Day 1: Introduction to Large Language Models (LLMs)

Laboratory: Systems setup, the Hugging Face library, a first exercise

Day 2: LLMs for content representation, classification and regression

Laboratory: Thematic clustering and classification of textual sources, regression analysis

Day 3: LLMs for content generation and data analysis

Laboratory: Prompt engineering, retrieval-augmented generation, data analysis. Course feedback and Q und A

Course methods / Learning activities

The course combines lectures (morning sessions) with laboratories consisting of live coding and practicals (afternoon sessions).

Prerequisites

A practical knowledge of the Python programming language is highly recommended.

Preliminary readings

• Riedl, “A very gentle introduction to Large Language Models”, 2023. https://mark-riedl.medium.com/a-very-gentle-introduction-to-large-language-models-without-the-hype-5f67941fa59e.
• Alammar and Grootendorst, “Hands-on Large Language Models”, O’Reily 2024. https://www.llm-book.com.

Dieses Angebot hat keine Wahl- und Anschlussmöglichkeiten.

Mo, 1.6.2026, 8.45–16.30 Uhr
Di, 2.6.2026, 8.45–16.30 Uhr
Mi, 3.6.2026, 8.45–16.30 Uhr

Campus Brugg-Windisch

Prof. Dr. Giovanni Colavizza, Professor of Computer Science at the Department of Communication (University of Copenhagen) und Associate, Professor of Computer Science at the Department of Classical and Italian Philology (University of Bologna).

• Dozierende an Hochschulen
• Mitarbeitende an Hochschulen

Erfahrungen in der qualitativen Forschung sind wünschenswert, aber keine zwingende Voraussetzung.

CHF 400

Alle Informationen als PDF

Die vollständigen Informationen zu diesem Angebot sind auch als druckbares PDF verfügbar.

PDF herunterladen

Dr. Jasmin Näpfli
+41 56 202 79 54
jasmin.naepfli@fhnw.ch

Zu diesem Angebot gibt es keine Info-Anlässe.