Understanding Politics via Contextualized Discourse Processing

TL;DR

This paper introduces a Compositional Reader model that enhances text representations by capturing nuanced political agendas and contextual information from multiple sources, improving understanding of entities, issues, and events.

Contribution

It presents a novel model architecture that processes multiple documents to generate contextualized representations for political discourse analysis, addressing limitations of existing PLMs.

Findings

Representations are meaningful and effective in capturing political nuances.

Model outperforms baseline methods in empirical evaluations.

Supports processing multiple documents for comprehensive entity and issue analysis.

Abstract

Politicians often have underlying agendas when reacting to events. Arguments in contexts of various events reflect a fairly consistent set of agendas for a given entity. In spite of recent advances in Pretrained Language Models (PLMs), those text representations are not designed to capture such nuanced patterns. In this paper, we propose a Compositional Reader model consisting of encoder and composer modules, that attempts to capture and leverage such information to generate more effective representations for entities, issues, and events. These representations are contextualized by tweets, press releases, issues, news articles, and participating entities. Our model can process several documents at once and generate composed representations for multiple entities over several issues or events. Via qualitative and quantitative empirical analysis, we show that these representations are meaningful and effective.