Ideology is at the core of political science research. Yet, there still does not exist general-purpose tools to characterize and predict ideology across different genres of text. To this end, we study Pretrained Language Models using novel ideology-driven pretraining objectives that rely on the comparison of articles on the same story written by media of different ideologies. We further collect a large-scale dataset, consisting of more than 3.6M political news articles, for pretraining. Our model POLITICS outperforms strong baselines and the previous state-of-the-art models on ideology prediction and stance detection tasks. Further analyses show that POLITICS is especially good at understanding long or formally written texts, and is also robust in few-shot learning scenarios.
@article{arxiv.2205.00619,
title = {POLITICS: Pretraining with Same-story Article Comparison for Ideology Prediction and Stance Detection},
author = {Yujian Liu and Xinliang Frederick Zhang and David Wegsman and Nick Beauchamp and Lu Wang},
journal= {arXiv preprint arXiv:2205.00619},
year = {2022}
}
Comments
Findings of NAACL'22. The first two authors contribute equally