LLM情感分析中的参照点：结构化上下文的作用
Reference Points in LLM Sentiment Analysis: The Role of Structured Context
AI总结：
本文研究结构化上下文对LLM情感分析的影响，发现JSON格式提示配合额外参照信息可使3B小模型在Yelp数据上超越未微调基线，为资源受限场景提供实用替代方案。
摘要：
大语言模型（LLMs）现已在包括营销研究在内的许多领域得到广泛应用。其中，情感分析尤其有助于企业理解消费者偏好。虽然大多数自然语言处理（NLP）研究仅从评论文本本身进行情感分类，但前景理论和期望—失验理论等营销理论指出，顾客评价不仅由实际体验塑造，还受到额外参照点的影响。因此，本研究探讨此类补充信息的内容和格式如何影响使用LLMs进行的情感分析。我们使用一个适合实际营销应用的轻量级3B参数模型，比较了自然语言（NL）提示和JSON格式提示。在两个Yelp类别（Restaurant和Nightlife）上的实验表明，带有额外信息的JSON提示在未进行微调的情况下优于所有基线：Macro-F1分别提升1.6%和4%，而RMSE分别下降16%和9.1%，使其可部署于资源受限的边缘设备中。此外，后续分析证实，性能提升源于真正的上下文推理，而非标签代理。本工作表明，结构化提示能够使较小模型取得具有竞争力的性能，为大规模模型部署提供了一种实用的替代方案。
英文摘要：
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.
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。
