Benchmark
VaccineStance
A manually annotated benchmark dataset specifically designed for stance detection on vaccine-related topics. It covers three stance categories—support, opposition, and neutral—and is used to evaluate models' stance recognition capabilities in context-sensitive, polarized opinion scenarios.
Timeline (last 90 days)
Oct 12
The research team contributed the VaccineStance dataset, a manually annotated benchmark specifically targeting vaccine stance detection.
Unverified50%
Oct 12
Both the VaccineStance dataset and the code for MoPrO-SD have been open-sourced on GitHub.
Unverified50%