Cost-Sensitive BERT for Generalisable Sentence Classification on Imbalanced Data

Harish Tayyar Madabushi, Elena Kochkina, Michael Castelle

Research output: Chapter or section in a book/report/conference proceedingChapter in a published conference proceeding


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.
Original languageEnglish
Title of host publicationProceedings of the Second Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda
Place of PublicationHong Kong, China
PublisherAssociation for Computational Linguistics
Number of pages10
Publication statusPublished - 1 Nov 2019


Dive into the research topics of 'Cost-Sensitive BERT for Generalisable Sentence Classification on Imbalanced Data'. Together they form a unique fingerprint.

Cite this