Team DoNotDistribute at SemEval-2020 Task 11: Features, Finetuning, and Data Augmentation in Neural Models for Propaganda Detection in News Articles

TL;DR

This paper describes a neural approach using BERT models and handcrafted features for detecting propaganda techniques in news articles, achieving strong results and providing insights through ablation studies.

Contribution

It introduces a combined BERT-based and feature-based method for propaganda detection, with detailed analysis of feature effectiveness and model performance.

Findings

Models outperform baselines in both subtasks

Ablation studies reveal feature importance

Discussion guides future propaganda detection research

Abstract

This paper presents our systems for SemEval 2020 Shared Task 11: Detection of Propaganda Techniques in News Articles. We participate in both the span identification and technique classification subtasks and report on experiments using different BERT-based models along with handcrafted features. Our models perform well above the baselines for both tasks, and we contribute ablation studies and discussion of our results to dissect the effectiveness of different features and techniques with the goal of aiding future studies in propaganda detection.