Open Source LLMs for Content Analysis

Ready-to-use, open source Large Language Models (LLMs) are an important research infrastructure. They are easy to access, adaptable, scalable, and inexpensive, while achieving a level of performance that can compete with manual content analysis.

This page provides step-by-step guides to using these models for content analysis. It is intended as a resource for researchers and practitioners in the social sciences and related fields who are interested in applying LLMs to analyze textual data.

Illustration of a transformer-style robot working on a laptop, symbolizing large language models.

Get started

Tutorials

Step-by-step walkthrough of common tasks across different model types — no prior experience required.

Begin a tutorial →

Paper

Supplementary website for the Publizistik article (in German): a step-by-step guide and empirical example study.

Read the supplement →

Workshop

A hands-on, interactive introduction to the workflow of using open-source LLMs for content analysis.

Explore the workshop →

Citation

For attribution, please cite this work as:

Possler, D., Dietrich, F., Scheper, J., Lammers, A., & Spatzenegger, A. (2026). Gebrauchsfertige, Open Source Large Language Models auf Hugging Face als Forschungsinfrastruktur für die standardisierte Inhaltsanalyse von Texten [Ready-to-use, open-source Large Language Models on Hugging Face as research infrastructure for standardized content analysis of text]. Publizistik. https://doi.org/10.1007/s11616-026-00942-w