This study investigates the use of Large Language Models (LLMs) for political stance detection in informal online discourse, where language is often sarcastic, ambiguous, and context-dependent. We explore whether providing contextual information, specifically user profile summaries derived from historical posts, can improve classification accuracy. Using a real-world political forum dataset, we generate structured profiles that summarize users' ideological leaning, recurring topics, and linguistic patterns. We evaluate seven state-of-the-art LLMs across baseline and context-enriched setups through a comprehensive cross-model evaluation. Our findings show that contextual prompts significantly boost accuracy, with improvements ranging from +17.5\% to +38.5\%, achieving up to 74\% accuracy that surpasses previous approaches. We also analyze how profile size and post selection strategies affect performance, showing that strategically chosen political content yields better results than larger, randomly selected contexts. These findings underscore the value of incorporating user-level context to enhance LLM performance in nuanced political classification tasks.

翻译：本研究探讨了大型语言模型（LLMs）在非正式在线政治话语立场检测中的应用，此类话语常具有讽刺性、模糊性和语境依赖性。我们重点探究通过提供上下文信息——特别是从用户历史发帖中提取的用户画像摘要——能否提升分类准确性。基于真实政治论坛数据集，我们构建了结构化用户画像，用以总结用户意识形态倾向、高频议题及语言模式。通过全面的跨模型评估，我们在基线设置和上下文增强设置下测试了七种前沿大型语言模型。实验结果表明，上下文提示能显著提升检测准确率，增幅区间为+17.5%至+38.5%，最高准确率达74%，超越现有方法。我们还分析了画像规模与发帖选择策略对性能的影响，证明经过策略筛选的政治内容比随机选取的大规模上下文能产生更优结果。这些发现凸显了在微妙的政治分类任务中，融入用户层级上下文对于提升大型语言模型性能的重要价值。