skip to content

Faculty of Economics

Journal Cover

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:

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

Papers and Publications

Recent Publications

Bhattacharya, D. The Empirical Content of Binary Choice Models Econometrica [2021]

Carvalho, V. M., Nirei, M., Saito, Y. U. and Tahbaz-Salehi, A. Supply Chain Disruptions: Evidence from the Great East Japan Earthquake Quarterly Journal of Economics [2021]

Boneva, L., Elliott, D., Kaminska, I., Linton, O., McLaren, N. and Morley, B. The Impact of Corporate QE on Liquidity: Evidence from the UK The Economic Journal [2022]

Mueller, H. and Rauh, C. The Hard Problem of Prediction for Conflict Prevention Journal of the European Economic Association [2022]