UstanceBR: a social media language resource for stance prediction

This work introduces UstanceBR, a novel social media corpus in the Brazilian Portuguese Twitter/X domain for target-based stance prediction. The corpus comprises 46.9 k labelled stances toward selected target topics, additional publications, and extensive network information about the 11.3 k users who published these stances on social media. In this study, we describe the corpus data and a number of usage examples for both in-domain and cross-target stance prediction based on text and network-related information, which are intended to provide initial baseline results for future studies in the field.