GerSti: A German Emotion Stimulus Corpus of News Headlines

A novel resource for emotion classification and sequence labeling




Bao Minh Doan Dang, Roman Klinger


Emotion stimulus detection became a popular task in emotion analysis recently, but most resources are only available in Mandarin and English. We contribute a German resource of token-level emotion stimulus annotations in a novel German news headline corpus and perform cross-lingual experiments in which we train on an English corpus and apply the model on our German resource.


Bao Minh Doan Dang, Laura Oberländer, and Roman Klinger.
Emotion stimulus detection in german news headlines. In Proceedings of the 17th Conference on Natural Language Processing (KONVENS 2021), Düsseldorf, Germany, 2021.
German Society for Computational Linguistics & Language Technology.

This image shows Roman Klinger

Roman Klinger

Prof. Dr.

Adjunct Professor

To the top of the page