From Fake to Hyperpartisan News Detection Using Domain Adaptation

TL;DR

This paper explores unsupervised domain adaptation techniques to transfer knowledge from fake news detection to hyperpartisan news detection, demonstrating improved performance through various methods and data augmentation.

Contribution

It investigates the effectiveness of multiple unsupervised domain adaptation methods for cross-task news classification without target labels, combining clustering and topic modeling for enhanced results.

Findings

UDA techniques improve cross-domain news detection performance

Data augmentation further enhances accuracy

Combining clustering and topic modeling yields better results

Abstract

Unsupervised Domain Adaptation (UDA) is a popular technique that aims to reduce the domain shift between two data distributions. It was successfully applied in computer vision and natural language processing. In the current work, we explore the effects of various unsupervised domain adaptation techniques between two text classification tasks: fake and hyperpartisan news detection. We investigate the knowledge transfer from fake to hyperpartisan news detection without involving target labels during training. Thus, we evaluate UDA, cluster alignment with a teacher, and cross-domain contrastive learning. Extensive experiments show that these techniques improve performance, while including data augmentation further enhances the results. In addition, we combine clustering and topic modeling algorithms with UDA, resulting in improved performances compared to the initial UDA setup.