Political Leaning and Politicalness Classification of Texts
–arXiv.org Artificial Intelligence
This paper addresses the challenge of automatically classifying text according to political leaning and politicalness using transformer models. We compose a comprehensive overview of existing datasets and models for these tasks, finding that current approaches create siloed solutions that perform poorly on out-of-distribution texts. To address this limitation, we compile a diverse dataset by combining 12 datasets for political leaning classification and creating a new dataset for politicalness by extending 18 existing datasets with the appropriate label. Through extensive benchmarking with leave-one-in and leave-one-out methodologies, we evaluate the performance of existing models and train new ones with enhanced generalization capabilities.
arXiv.org Artificial Intelligence
Jul-21-2025
- Country:
- Europe (1.00)
- North America > United States
- Maryland (0.28)
- Genre:
- Research Report > New Finding (1.00)
- Industry:
- Government (1.00)
- Media > News (0.93)
- Technology: