用向量方向分析情感，跨语种跨时代都有效。
Is Sentiment Banana-Shaped? Exploring the Geometry and Portability of Sentiment Concept Vectors
- 将情感建模为嵌入空间中的方向向量，生成连续多语言评分。
- 不同语料库间迁移时性能损失小，验证了方法的通用性。
- 发现线性假设近似成立，适合人文社科领域的情感分析。
人文领域的情感分析常需上下文敏感的连续评分。概念向量投影（CVP）提供了一种新方案：通过将情感建模为嵌入空间中的方向，生成与人类判断高度一致的连续、多语言评分。然而该方法在不同领域间的可迁移性及其基础假设仍不明确。我们评估了CVP在不同文体、历史时期、语言及情感维度上的表现，发现基于某一语料库训练的概念向量能良好迁移到其他语料库，性能损失极小。为进一步理解泛化规律，我们检验了支撑CVP的线性假设。结果表明，尽管CVP具有良好的可迁移性并能捕捉普遍模式，其线性假设仅为近似成立，提示未来仍有改进空间。代码已开源：github.com/lauritswl/representation-transfer
原文摘要 · Abstract (English)
Use cases of sentiment analysis in the humanities often require contextualized, continuous scores. Concept Vector Projections (CVP) offer a recent solution: by modeling sentiment as a direction in embedding space, they produce continuous, multilingual scores that align closely with human judgments. Yet the method's portability across domains and underlying assumptions remain underexplored. We evaluate CVP across genres, historical periods, languages, and affective dimensions, finding that concept vectors trained on one corpus transfer well to others with minimal performance loss. To understand the patterns of generalization, we further examine the linearity assumption underlying CVP. Our findings suggest that while CVP is a portable approach that effectively captures generalizable patterns, its linearity assumption is approximate, pointing to potential for further development. Code available at: github.com/lauritswl/representation-transfer
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。