CLoSE: Contrastive Learning of Subframe Embeddings for Political Bias Classification of News Media

Michelle YoungJin Kim, Kristen Marie Johnson


Abstract
Framing is a political strategy in which journalists and politicians emphasize certain aspects of a societal issue in order to influence and sway public opinion. Frameworks for detecting framing in news articles or social media posts are critical in understanding the spread of biased information in our society. In this paper, we propose CLoSE, a multi-task BERT-based model which uses contrastive learning to embed indicators of frames from news articles in order to predict political bias. We evaluate the performance of our proposed model on subframes and political bias classification tasks. We also demonstrate the model’s classification accuracy on zero-shot and few-shot learning tasks, providing a promising avenue for framing detection in unlabeled data.
Anthology ID:
2022.coling-1.245
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
2780–2793
Language:
URL:
https://aclanthology.org/2022.coling-1.245
DOI:
Bibkey:
Cite (ACL):
Michelle YoungJin Kim and Kristen Marie Johnson. 2022. CLoSE: Contrastive Learning of Subframe Embeddings for Political Bias Classification of News Media. In Proceedings of the 29th International Conference on Computational Linguistics, pages 2780–2793, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
CLoSE: Contrastive Learning of Subframe Embeddings for Political Bias Classification of News Media (Kim & Johnson, COLING 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/auto-file-uploads/2022.coling-1.245.pdf
Code
 msu-nlp-css/close_framing