Tool developed in the paper:

Widmann, Tobias, and Maximilian Wich. 2022. “Creating and Comparing Dictionary, Word Embedding, and Transformer-Based Models to Measure Discrete Emotions in German Political Text.” Political Analysis, June, 1–16. https://doi.org/10.1017/pan.2022.15.

Please start by reading this article which contains information about the crowd-coded data used to fine-tune the model. The model is free to use for academic research. In case you use it, please always cite the article above.

In order to obtain all necessary files, follow the link to the Github repo. The repository contains all files and code to apply the transformer model.

Tobias Widmann
Tobias Widmann
Assistant Professor in Political Science

My research interests include political rhetoric, emotions & morality, and computational text analysis.