skip to content

Faculty of Economics

Journal Cover

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

Adversarial Training for News Stance Detection: Leveraging Signals from a Multi-Genre Corpus

Proceedings of the EACL Hackashop on News Media Content Analysis and Automated Report Generation

pp. 1-7 (2020)

Abstract: Cross-target generalization constitutes an important issue for news Stance Detection (SD). In this short paper, we investigate adversarial cross-genre SD, where knowledge from annotated user-generated data is leveraged to improve news SD on targets unseen during training. We implement a BERT-based adversarial network and show experimental performance improvements over a set of strong baselines. Given the abundance of user-generated data, which are considerably less expensive to retrieve and annotate than news articles, this constitutes a promising research direction.

Author links: Chryssi Giannitsarou  Flavio Toxvaerd  

Publisher's Link: https://aclanthology.org/2021.hackashop-1.1

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


Papers and Publications



Recent Publications


Huffman, D., Raymond, C. and Shvets, J. Persistent Overconfidence and Biased Memory: Evidence from Managers American Economic Review [2022]

Bhattacharya, D. and Shvets, J. Inferring Trade-Offs in University Admissions: Evidence from Cambridge Journal of Political Economy, accepted [2024]

Gallo, E. and Yan, C. Efficiency and Equilibrium in Network Games: An Experiment Review of Economics and Statistics [2023]

Evans, R. A. and Reiche, S. K. When Is a Contrarian Adviser Optimal? American Economic Journal: Microeconomics [2023]