Cost-Sensitive BERT for Generalisable Sentence Classification with Imbalanced Data

TL;DR

This paper enhances BERT's ability to classify propaganda sentences across diverse and imbalanced datasets by introducing cost-sensitive training and dataset similarity measures, improving generalization in evolving news contexts.

Contribution

It proposes a cost-weighting method for BERT and a dataset similarity measure to improve generalization in imbalanced, dissimilar data scenarios.

Findings

Achieved second-highest score on Propaganda Techniques Corpus

Demonstrated improved generalization with cost-sensitive BERT

Showed effectiveness of dataset similarity measure in classification

Abstract

The automatic identification of propaganda has gained significance in recent years due to technological and social changes in the way news is generated and consumed. That this task can be addressed effectively using BERT, a powerful new architecture which can be fine-tuned for text classification tasks, is not surprising. However, propaganda detection, like other tasks that deal with news documents and other forms of decontextualized social communication (e.g. sentiment analysis), inherently deals with data whose categories are simultaneously imbalanced and dissimilar. We show that BERT, while capable of handling imbalanced classes with no additional data augmentation, does not generalise well when the training and test data are sufficiently dissimilar (as is often the case with news sources, whose topics evolve over time). We show how to address this problem by providing a statistical measure of similarity between datasets and a method of incorporating cost-weighting into BERT when the training and test sets are dissimilar. We test these methods on the Propaganda Techniques Corpus (PTC) and achieve the second-highest score on sentence-level propaganda classification.