利用大型语言模型解读新闻中的政治实体情感：零样本与少样本策略
Deciphering Political Entity Sentiment in News with Large Language Models: Zero-Shot and Few-Shot Strategies
AI总结：
本文评估 LLM 用零样本、少样本及 COT 提示识别政治新闻中实体情感的效果，证明其优于微调 BERT，并分析上下文学习与自洽机制的作用。
摘要：
情感分析在理解公众舆论方面发挥着关键作用，尤其是在政治领域，新闻文章对实体的描绘会影响公众认知。本文研究大型语言模型（LLM）从政治新闻文章中预测实体特定情感的有效性。我们利用零样本和少样本策略，探索 LLM 辨别新闻内容中对政治实体情感的能力。通过在少样本上下文学习中采用辅以理由的思维链（COT）方法，我们评估该方法是否能提高情感预测准确率。我们在带有情感标签的数据集上的评估表明，LLM 在捕捉实体特定情感方面优于经过微调的 BERT 模型。我们发现，上下文学习显著提升了模型性能，而自洽机制增强了情感预测的一致性。尽管结果令人鼓舞，我们也观察到 COT 提示方法的有效性存在不一致。总体而言，研究结果突显了 LLM 在政治新闻领域以实体为中心的情感分析中的潜力，并强调了合适的提示策略与模型架构的重要性。
英文摘要：
Sentiment analysis plays a pivotal role in understanding public opinion, particularly in the political domain where the portrayal of entities in news articles influences public perception. In this paper, we investigate the effectiveness of Large Language Models (LLMs) in predicting entity-specific sentiment from political news articles. Leveraging zero-shot and few-shot strategies, we explore the capability of LLMs to discern sentiment towards political entities in news content. Employing a chain-of-thought (COT) approach augmented with rationale in few-shot in-context learning, we assess whether this method enhances sentiment prediction accuracy. Our evaluation on sentiment-labeled datasets demonstrates that LLMs, outperform fine-tuned BERT models in capturing entity-specific sentiment. We find that learning in-context significantly improves model performance, while the self-consistency mechanism enhances consistency in sentiment prediction. Despite the promising results, we observe inconsistencies in the effectiveness of the COT prompting method. Overall, our findings underscore the potential of LLMs in entity-centric sentiment analysis within the political news domain and highlight the importance of suitable prompting strategies and model architectures.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
