用结构化提示提升小模型情感分析能力，更贴近真实消费评价逻辑。
Reference Points in LLM Sentiment Analysis: The Role of Structured Context
- 用JSON格式提供参考信息，增强模型上下文理解
- 性能比基线高1.6%-4%，误差降低9.1%-16%
- 适合资源有限的营销场景快速部署
大语言模型已广泛应用于多个领域，包括营销研究。情感分析有助于企业了解消费者偏好。尽管多数NLP研究仅基于评论文本进行分类，但营销理论（如前景理论和期望-确认理论）指出，客户评价不仅受实际体验影响，还受额外参考点影响。本研究探讨了这些补充信息的内容与格式如何影响基于LLM的情感分析效果。采用轻量级3B参数模型，在两个Yelp类别（餐厅与夜生活）上对比自然语言（NL）与JSON格式提示。结果表明，包含额外信息的JSON提示在无微调情况下优于所有基线：宏平均F1提升1.6%与4%，均方根误差下降16%与9.1%，具备在资源受限的边缘设备上部署的能力。后续分析确认性能提升源于真正的上下文推理而非标签代理。该工作表明，结构化提示可使小型模型达到竞争性表现，为大规模模型部署提供实用替代方案。
原文摘要 · Abstract (English)
Large language models (LLMs) are now widely used across many fields, including marketing research. Sentiment analysis, in particular, helps firms understand consumer preferences. While most NLP studies classify sentiment from review text alone, marketing theories, such as prospect theory and expectation--disconfirmation theory, point out that customer evaluations are shaped not only by the actual experience but also by additional reference points. This study therefore investigates how the content and format of such supplementary information affect sentiment analysis using LLMs. We compare natural language (NL) and JSON-formatted prompts using a lightweight 3B parameter model suitable for practical marketing applications. Experiments on two Yelp categories (Restaurant and Nightlife) show that the JSON prompt with additional information outperforms all baselines without fine-tuning: Macro-F1 rises by 1.6% and 4% while RMSE falls by 16% and 9.1%, respectively, making it deployable in resource-constrained edge devices. Furthermore, a follow-up analysis confirms that performance gains stem from genuine contextual reasoning rather than label proxying. This work demonstrates that structured prompting can enable smaller models to achieve competitive performance, offering a practical alternative to large-scale model deployment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。