A Deep Modular RNN Approach for Ethos Mining

Abstract

Automatically recognising and extracting the reasoning expressed in natural language text is extremely demanding and only very recently has there been significant headway. While such argument mining focuses on logos (the content of what is said) evidence has demonstrated that using ethos (the character of the speaker) can sometimes be an even more powerful tool of influence. We study the UK parliamentary debates which furnish a rich source of ethos with linguistic material signalling the ethotic relationships between politicians. We then develop a novel deep modular recurrent neural network, DMRNN, approach and employ proven methods from argument mining and sentiment analysis to create an ethos mining pipeline. Annotation of ethotic statements is reliable and its extraction is robust (macro-F1 = 0.83), while annotation of polarity is perfect and its extraction is solid (macro-F1 = 0.84). By exploring correspondences between ethos in political discourse and major events in the political landscape through ethos analytics, we uncover tantalising evidence that identifying expressions of positive and negative ethotic sentiment is a powerful instrument for understanding the dynamics of governments.

Exploring the Role of Argument Structure in Online Debate Persuasion

“…Argument structures, which can be considered as a special kind of discourse structure, have been widely analyzed in the task of automatic essay scoring and feedback (Klebanov et al, 2016;Ghosh et al, 2016;Wachsmuth et al, 2016). Furthermore, Duthie and Budzynska (2018) has studied the relationship between ethos, a specific kind of argument unit, and the dynamics of governments from the UK parliamentary debates. The role of argument structure in persuasion on online debates is much less explored, which is the main focus of this paper.…”

GPolS: A Contextual Graph-Based Language Model for Analyzing Parliamentary Debates and Political Cohesion

“…A developing body of research at the intersection of Politics and Linguistics spans agreement detection (Menini and Tonelli, 2016;M. and M., 2018;Duthie and Budzynska, 2018), emotion analysis (Rheault, 2016;Dzieciatko, 2019), topic-opinion analysis (Nguyen et al, 2015;Abercrombie and Batista-Navarro, 2018b) and, debate stance classification (Proksch et al, 2019). Existing work focuses on these tasks through legislative speeches from the US Congress (Chen et al, 2017), the UK Parliament (Bhavan et al, 2019), and the EU Parliament (Glavaš et al, 2017;Frid-Nielsen, 2018) and through social media such as Twitter (Trilling, 2014;Boutyline and Willer, 2017).…”

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts

“…This, then, is argument mining: identifying that an argument is present, de-composing an argument into its constituent parts, determining how those parts are connected and structured -and how they connect with other arguments and argument parts -and finally, evaluating the quality of those connections. Thorough overviews are provided in, e.g., (Stede and Schneider, 2018;Lippi and Torroni, 2016) with a wide range of more detailed themes covered elsewhere, such as premise-conclusion recovery (Stab and Gurevych, 2017), types of argumentation pattern (Walton et al, 2008), relationships between semantic and argumentative structures (Becker et al, 2017), how ethos of speakers interacts with argument structure (Duthie and Budzynska, 2018) and automated assessment of argument persuasiveness (Carlile et al, 2018).…”