Conforti, C., Berndt, J., Pilehvar, M. T., Giannitsarou, C., Toxvaerd, F. and Collier, N.

Synthetic Examples Improve Cross-Target Generalization: A Study on Stance Detection on a Twitter corpus

Proceedings of the Eleventh Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis

pp. 181-187 (2020)

Abstract: Cross-target generalization is a known problem in stance detection (SD), where systems tend to perform poorly when exposed to targets unseen during training. Given that data annotation is expensive and time-consuming, finding ways to leverage abundant unlabeled in-domain data can offer great benefits. In this paper, we apply a weakly supervised framework to enhance cross-target generalization through synthetically annotated data. We focus on Twitter SD and show experimentally that integrating synthetic data is helpful for cross-target generalization, leading to significant improvements in performance, with gains in F1 scores ranging from +3.4 to +5.1.

Author links: Chryssi Giannitsarou  Flavio Toxvaerd  

Publisher's Link: https://aclanthology.org/2021.wassa-1.19

Keynes Fund Project(s):
Mapping of Rumours and Information Diffusion (JHOQ)