Personal attacks have become a notable feature of U.S. presidential debates and play an important role in shaping public perception during elections. Detecting such attacks can improve transparency in political discourse and provide insights for journalists, analysts and the public. Advances in deep learning and transformer-based models, particularly BERT and large language models (LLMs) have created new opportunities for automated detection of harmful language. Motivated by these developments, we present a framework for analysing personal attacks in U.S. presidential debates. Our work involves manual annotation of debate transcripts across the 2016, 2020 and 2024 election cycles, followed by statistical and language-model based analysis. We investigate the potential of fine-tuned transformer models alongside general-purpose LLMs to detect personal attacks in formal political speech. This study demonstrates how task-specific adaptation of modern language models can contribute to a deeper understanding of political communication.

Rhetorical strategies are central to persuasive communication, from political discourse and marketing to legal argumentation. However, analysis of rhetorical strategies has been limited by reliance on human annotation, which is costly, inconsistent, difficult to scale. Their associated datasets are often limited to specific topics and strategies, posing challenges for robust model development. We propose a novel framework that leverages large language models (LLMs) to automatically generate and label synthetic debate data based on a four-part rhetorical typology (causal, empirical, emotional, moral). We fine-tune transformer-based classifiers on this LLM-labeled dataset and validate its performance against human-labeled data on this dataset and on multiple external corpora. Our model achieves high performance and strong generalization across topical domains. We illustrate two applications with the fine-tuned model: (1) the improvement in persuasiveness prediction from incorporating rhetorical strategy labels, and (2) analyzing temporal and partisan shifts in rhetorical strategies in U.S. Presidential debates (1960-2020), revealing increased use of affective over cognitive argument in U.S. Presidential debates.

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.

Body language experts told Dr. Phil Tuesday after the presidential debate that the ABC News moderators clearly favored Vice President Kamala Harris. Dr. Phil spoke with experts Scott Rouse and Greg Hartley in a special post-debate town hall broadcast. Rouse holds multiple certificates in advanced interrogation training and has been trained alongside the FBI, Secret Service, U.S. Military Intelligence, and the Department of Defense. Hartley is a former Army interrogator with expertise in intelligence, business, body language and behavior. When asked whether they saw bias from moderators David Muir and Linsey Davis in Tuesday's debate, Hartley said they were against former President Trump.

Large language models have demonstrated remarkable capabilities in natural language processing, yet their application to political discourse analysis remains underexplored. This paper introduces a novel approach to evaluating presidential debate performances using LLMs, addressing the longstanding challenge of objectively assessing debate outcomes. We propose a framework that analyzes candidates' "Policies, Persona, and Perspective" (3P) and how they resonate with the "Interests, Ideologies, and Identity" (3I) of four key audience groups: voters, businesses, donors, and politicians. Our method employs large language models to generate the LLM-POTUS Score, a quantitative measure of debate performance based on the alignment between 3P and 3I. We apply this framework to analyze transcripts from recent U.S. presidential debates, demonstrating its ability to provide nuanced, multi-dimensional assessments of candidate performances. Our results reveal insights into the effectiveness of different debating strategies and their impact on various audience segments. This study not only offers a new tool for political analysis but also explores the potential and limitations of using LLMs as impartial judges in complex social contexts. In addition, this framework provides individual citizens with an independent tool to evaluate presidential debate performances, which enhances democratic engagement and reduces reliance on potentially biased media interpretations and institutional influence, thereby strengthening the foundation of informed civic participation.

The first 2024 presidential debate unfolded Thursday night between President Joe Biden and former President Donald Trump and it was, as fellow Slate writer Jill Filipovic put it, the "most painful two hours of television in living memory." If you missed it, good for you. If you did watch it, you'd be forgiven for not remembering the topics that were actually debated vaguely shouted about. In between Biden's excruciatingly painful and "nightmarishly confused" performance and Trump's boorish firehose of lies and falsehoods, the debate also ostensibly featured a wide range of topics like abortion, the economy, climate change, foreign policy in Ukraine and Israel, election integrity, immigration, veterans, race, crime, health care, and even which of the two candidates has a better golf game. However, there was one major issue that the debate failed to broach--despite the fact that it's one of the most (if not the most) consequential developments since the last election cycle: artificial intelligence.

It's that time again for Americans to take to the polls. If you've lived long enough, you recognize the patterns… Each opposing political side, shades the other, scandals and leaks may pop, shortcomings are magnified, critics make the news, promises are doled out'rather-convincingly' and there's an overwhelming sense of'nationality and togetherness' touted by both sides… And often, we simply choose the'lesser of the two evils', because candidly the one is not significantly better than the other. So today, I'm going to analyze the presidential debates of President Trump and Vice-President Biden… The entire analysis is done by the Author, using scientific methods that do not assume faultlessness. This is a personal project devoid of any political affiliations, sentiments or undertones. The inferences expressed from this scientific process are entirely the Author's, based on the data.

In a midnight tweet, the President of the United States revealed that he and the First Lady have both tested positive for the coronavirus, raising concerns about his health and upending an already chaotic campaign season just thirty-two days before the election. The virus--which has transformed American life, killed more than two hundred thousand Americans, and devastated the U.S. economy--now threatens the health of the President and senior government officials. The White House has said that the President is experiencing mild symptoms; even so, they are signs of COVID-19, the disease caused by the coronavirus. From here, his illness might dissipate or grow much more severe. For the moment, President Trump's illness is mild.

The first presidential debate between President Trump and former Vice President Joe Biden has concluded. Following the night, the biggest takeaway is that there were no surprises, and nothing happened that will change any attitudes, cause either candidate to gain or lose any votes, or move any undecided voters one way or the other. Indeed, while the debate was contentious, and at times became personal, it lacked any real substance that could change attitudes in any meaningful way. Given the level of back-and-forth between the candidates, the substance of the candidates' answers was often lost and took a back seat to their style of argumentation and command of the room. Though, in terms of style, in my view, President Trump was the clear winner--Trump was in command of the conversation, in control of the discussion, and if not presidential, certainly more in command.

PBS NewsHour full episode, May 25, 2017 Live now PBS NewsHour full episode, May 25, 2017 Show more This item has been hidden Uploads Play all 55:04 PBS NewsHour full episode May 25, 2017 - Duration: 55 minutes. PBS NewsHour full episode, May 25, 2017 4:57 Why the lessons of Mister Rogers never go away - Duration: 4 minutes, 57 seconds. Streamed 6 hours ago This item has been hidden Political analysis with Mark Shields and David Brooks Play all 12:22 Shields and Brooks on the barrage of Trump revelations - Duration: 12 minutes. This item has been hidden Brief but Spectacular Play all 3:30 Will artificial intelligence help us solve every problem? - Duration: 3 minutes, 30 seconds. This item has been hidden ScienceScope Play all 5:46 These cement-making bacteria could build the cities of the future - Duration: 5 minutes, 46 seconds.