DeInStance: Creating and Evaluating a German Corpus for Fine-Grained Inferred Stance Detection

We introduce deInStance, a corpus of 1000 politicians’ answers in German (de) containing sentences labeled with explicitly expressed and inferred stances - pro and con relations - by 3 annotators. They achieved an acceptable inter-rater agreement given the inherent subjective nature of the task. A first baseline, a fine-tuned BERT-based token classifier, achieved F1-scores of around 70% . Our focus is on the difficult subclass of sentences comprising only non-polar words, but still with an (implicit) pro or con perspective of the writer.