Predicting Stance Change Using Modular Architectures

Aldo Porco     Dan Goldwasser    
International Conference on Computational Linguistics (CoLING), 2020
[pdf]

Abstract

The ability to change a person’s mind on a given issue depends both on the arguments they are presented with and on their underlying perspectives and biases on that issue. Predicting stance changes require characterizing both aspects and the interaction between them, especially in realistic settings in which stance changes are very rare. In this paper, we suggest a modular learning approach, which decomposes the task into multiple modules, focusing on different aspects of the interaction between users, their beliefs, and the arguments they are exposed to. Our experiments show that our modular approach archives significantly better results compared to the end-to-end approach using BERT over the same inputs.


Bib Entry

  @InProceedings{PG_coling_2020,
    author = "Aldo Porco and Dan Goldwasser",
    title = "Predicting Stance Change Using Modular Architectures",
    booktitle = "International Conference on Computational Linguistics (CoLING)",
    year = "2020"
  }