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

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