Solomon at SemEval-2020 Task 11: Ensemble Architecture for Fine-Tuned Propaganda Detection in News Articles

Proceedings of the 14th International Workshop on Semantic Evaluation, pages 1802–1807 Barcelona, Spain (Online), December 12, 2020. 1802 Solomon at SemEval-2020 Task 11: Ensemble Architecture for Fine-Tuned Propaganda Detection in News Articles Mayank Raj∗ Ankita Gupta Ajay Jaiswal∗ Sudeep Kumar Sahoo Rohit R.R Vertika Srivastava Yeon Hyang Kim Samsung R&D Institute India, Bangalore { mayank.raj, ajay.jaiswal, rohit.r.r, gupta.ankita, sudeep.sahoo, v.srivastava, purine.kim}@samsung.com Abstract This paper describes our system (Solomon) details and results of participation in the SemEval 2020 Task 11 ”Detection of Propaganda Techniques in News Articles”(Da San Martino et al., 2020). We participated in Task ”Technique Classification” (TC) which is a multi-class classification task. To address the TC task, we used RoBERTa based transformer architecture for fine-tuning on the propaganda dataset. The predictions of RoBERTa were further fine-tuned by class-dependent- minority-class classifiers. A special classifier, which employs dynamically adapted Least Common Sub-sequence algorithm, is used to adapt to the intricacies of repetition class. Compared to the other participating systems, our submission is ranked 4th on the leaderboard. 1 Introduction In today’s digital world, information is being shared more rapidly across boundaries owing to the rampant use of social media platforms. While these platforms provide a forum for people to exchange their views with ease, they also serve as a medium for spreading misinformation in the absence of proper quality control mechanisms. Two paradigms of misinformation are often reported, fake news and propaganda. While fake news corresponds to factually incorrect information, propaganda is more nuanced. It aims at advancing a specific agenda using psychological and rhetorical techniques (e.g use of biased or loaded language, repetition etc) and may not be always factually wrong. Prior efforts have been made to segregate propagandist content (Rashkin et al., 2017), (Barr´on-Cedeno et al., 2019), (Habernal et al., 2017) from non-propagandist. These methods use distant supervision based techniques to obtain document level labels, often labelling all articles from a propagandist news outlet as propaganda. However, such techniques introduce inevitable noise (Horne et al., 2018). To this end, (Da San Martino et al., 2019) have introduced a propaganda dataset where they label propaganda techniques at fragment level, thus providing finer control and explainability. For example, following is an instance of propaganda with type “Slogan”. Trump tweeted, “ make America great again ! � �� � Slogan ” In this work we address the ”Technique Classification” (TC) task whose objective is to identify the propaganda technique employed in a fragment of text surrounded by its context. In the above example, “make America great again” is the fragment in which slogan technique has been employed. It is surrounded by its context “Trump tweeted”. The problem is modelled as a 14-class classification task. Our contributions in this work are summarized as follows : • We employ transfer learning by fine-tuning Transformer based language model, RoBERTa (Liu et al., 2019) on the propaganda dataset. ∗*Equal Contribution This work is licensed under a Creative Commons Attribution 4.0 International Licence.License details: http://creativecommons.org/licenses/by/4.0/. 1803 Figure 1: System Architecture with Precedence Order of Components • …

Content truncated to 500 words