Semantically Enriching Investor Micro-blogs for Opinion-Aware Emotion Analysis: A Practical Approach

通过语义增强投资者微博以实现观点感知的情感分析：一种实用方法

Abstract: While sentiment analysis is the staple of financial NLP, capturing the nuances of ‘why’ behind that sentiment remains a challenge. There have been attempts to address this by analysing investor emotions alongside sentiment; however, this does not provide the additional granularity required to understand the target of the emotion/sentiment.

摘要： 虽然情感分析是金融自然语言处理（NLP）的核心，但捕捉情感背后的“原因”细微差别仍然是一个挑战。此前已有研究尝试通过分析投资者情绪与情感来解决这一问题；然而，这种方法无法提供理解情感/情绪目标所需的额外粒度。

We address this by augmenting the StockEmotions dataset with semantically structured opinion graphs, which provide granular semantic depth to the existing sentiment and emotion labels. Using a declarative LLM pipeline, we augment the StockEmotions dataset with opinion graphs for each sentence, derived from 10,000 comments collected from StockTwits.

我们通过利用语义结构化的观点图（opinion graphs）来增强 StockEmotions 数据集，从而解决了这一问题。这些观点图为现有的情感和情绪标签提供了细粒度的语义深度。我们使用声明式大语言模型（LLM）流水线，从 StockTwits 收集的 10,000 条评论中提取观点图，并将其整合到 StockEmotions 数据集中。

In addition, we study the effect of introducing opinion semantics on baseline classifiers using Graph Neural Networks (GNNs). Our analysis demonstrates that incorporating opinion semantics improves classification performance across different emotional spectrums.

此外，我们还研究了引入观点语义对使用图神经网络（GNN）的基准分类器的影响。我们的分析表明，整合观点语义能够提升在不同情绪谱系下的分类性能。

---

Paper Details:

• Authors: Gaurav Negi, Paul Buitelaar
• arXiv ID: 2605.03092
• Subject: Computation and Language (cs.CL)
• Submission Date: 4 May 2026

论文详情：

• 作者： Gaurav Negi, Paul Buitelaar
• arXiv ID： 2605.03092
• 学科： 计算与语言 (cs.CL)
• 提交日期： 2026年5月4日