A Corpus of Persuasion Techniques in Slavic Languages

Abstract

We present a new corpus of persuasion techniques for Slavic languages. The corpus contains documents from parliamentary debates in Bulgarian and Polish, and from social media in Russian, annotated with persuasion techniques at text-span and sentence level. The techniques come from a taxonomy of 25 fine-grained persuasion techniques, grouped under six broader categories of rhetorical persuasion strategies. The corpus contains approximately 7500 text spans annotated with persuasion techniques, from 222 documents that cover hotly debated topics at both international and national level. We describe the process of corpus creation, provide related statistics, elaborate on topic and persuasion technique correlations. We provide baseline models and benchmark results for detection and classification of persuasion techniques at the text-span level and sentence level, which use classic ML-based and generative AI-based models.

Resources

Details