BPGC at SemEval-2020 Task 11: Propaganda Detection in News Articles with Multi-Granularity Knowledge Sharing and Linguistic Features Based Ensemble Learning

Proceedings of the 14th International Workshop on Semantic Evaluation, pages 1722–1731 Barcelona, Spain (Online), December 12, 2020. 1722 BPGC at SemEval-2020 Task 11: Propaganda Detection in News Articles with Multi-Granularity Knowledge Sharing and Linguistic Features based Ensemble Learning Rajaswa Patil1 and Somesh Singh2 and Swati Agarwal2 1Department of Electrical & Electronics Engineering 2Department of Computer Science & Information Systems BITS Pilani K. K. Birla Goa Campus, India {f20170334, f20180175, swatia}@goa.bits-pilani.ac.in Abstract Propaganda spreads the ideology and beliefs of like-minded people, brainwashing their audiences, and sometimes leading to violence. SemEval 2020 Task-11 aims to design automated systems for news propaganda detection. Task-11 consists of two sub-tasks, namely, Span Identification - given any news article, the system tags those specific fragments which contain at least one propaganda technique and Technique Classification - correctly classify a given propagandist statement amongst 14 propaganda techniques. For sub-task 1, we use contextual embeddings extracted from pre-trained transformer models to represent the text data at various granularities and propose a multi-granularity knowledge sharing approach. For sub-task 2, we use an ensemble of BERT and logistic regression classifiers with linguistic features. Our results reveal that the linguistic features are the reliable indicators for covering minority classes in a highly imbalanced dataset. 1 Introduction Propaganda is biased information that deliberately propagates a particular ideology or political orientation (Aggarwal and Sadana, 2019). Propaganda aims to influence the public’s mentality and emotions, targeting their reciprocation due to their personal beliefs (Jowett and O’donnell, 2018). News propaganda is a sub-type of propaganda that manipulates lies, semi-truths, and rumors in the disguise of credible news (Bakir et al., 2019). The emphasis on this manipulation differentiates propaganda and its various classes from each other and free verbalization (Hackett, 1984). News propaganda can lead to the mass circulation of misleading information, shared agenda, conflicts, religious or ethnic reasons, and can further even lead to violence and terrorism. Due to massive size, high velocity, rich online user interaction, and diversity, the manual identification of propaganda techniques is overwhelmingly impractical. Hence, the development of a generalized system for propaganda detection in news articles is a vital task for security analysts and society (Barr´on-Cedeno et al., 2019). In SemEval2020-Task11, Da San Martino et al. (2020) propose a corpus of 550 news articles for propaganda detection. Each article is annotated with propaganda spans belonging to 14 propaganda techniques. The annotation is performed at the fragment level. The task of propaganda detection is divided into two sub-tasks; Span identification (sequence labeling) and technique classification (sequence classification). Span identification sub-task aims to detect the propagandist spans of text in the news articles. Whereas, the technique classification sub-task aims to classify the propaganda spans into various propaganda techniques. The work presented in this paper aims to provide independent approaches for both sub-tasks 1 and 2. Most recent approaches for propaganda detection task use pre-trained transformer models. This work propose a multi-granularity knowledge sharing model built on top of the embeddings extracted from these transformer models for the propaganda span detection sub-task. Further, …

Content truncated to 500 words