Analyzing Biases in Political Dialogue: Tagging U.S. Presidential Debates with an Extended DAMSL Framework

TL;DR

This paper introduces BEADS, a novel annotation framework extending DAMSL to analyze biases and adversarial tactics in U.S. presidential debates, revealing Trump's dominant rhetorical strategies.

Contribution

The paper presents BEADS, a new domain-agnostic annotation framework for systematic bias detection in political discourse, validated through human and AI-assisted analysis of presidential debates.

Findings

Trump dominates in adversarial and bias categories

BEADS effectively captures ideological and emotional rhetoric

AI-assisted tagging matches human annotation accuracy

Abstract

We present a critical discourse analysis of the 2024 U.S. presidential debates, examining Donald Trump's rhetorical strategies in his interactions with Joe Biden and Kamala Harris. We introduce a novel annotation framework, BEADS (Bias Enriched Annotation for Dialogue Structure), which systematically extends the DAMSL framework to capture bias driven and adversarial discourse features in political communication. BEADS includes a domain and language agnostic set of tags that model ideological framing, emotional appeals, and confrontational tactics. Our methodology compares detailed human annotation with zero shot ChatGPT assisted tagging on verified transcripts from the Trump and Biden (19,219 words) and Trump and Harris (18,123 words) debates. Our analysis shows that Trump consistently dominated in key categories: Challenge and Adversarial Exchanges, Selective Emphasis, Appeal to Fear, Political Bias, and Perceived Dismissiveness. These findings underscore his use of emotionally charged and adversarial rhetoric to control the narrative and influence audience perception. In this work, we establish BEADS as a scalable and reproducible framework for critical discourse analysis across languages, domains, and political contexts.