分析美国总统辩论中的个人攻击

个人攻击已成为美国总统辩论中的一个显著特征，在选举期间在塑造公众认知方面发挥着重要作用。检测此类攻击有助于提高政治话语的透明度，并为记者、分析人士和公众提供洞察。深度学习和基于 Transformer 的模型，尤其是 BERT 和大语言模型（LLMs），为自动化检测有害语言创造了新的机会。ederated by these developments, we present a framework for analyzing 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.