DUTH at SemEval-2020 Task 11: BERT with Entity Mapping for Propaganda Classification

TL;DR

This paper presents a method for propaganda technique classification in news articles using BERT with entity mapping, combining NLP preprocessing, feature selection, and supervised learning to improve accuracy.

Contribution

The study introduces a novel approach integrating entity mapping with BERT for propaganda detection, enhancing classification performance over previous methods.

Findings

BERT with entity mapping outperforms baseline models

Entity recognition improves classification accuracy

Effective NLP preprocessing reduces dataset noise

Abstract

This report describes the methods employed by the Democritus University of Thrace (DUTH) team for participating in SemEval-2020 Task 11: Detection of Propaganda Techniques in News Articles. Our team dealt with Subtask 2: Technique Classification. We used shallow Natural Language Processing (NLP) preprocessing techniques to reduce the noise in the dataset, feature selection methods, and common supervised machine learning algorithms. Our final model is based on using the BERT system with entity mapping. To improve our model's accuracy, we mapped certain words into five distinct categories by employing word-classes and entity recognition.