构建细粒度身体情绪数据集，提升文本情绪识别精度。
CHEER-Ekman: Fine-grained Embodied Emotion Classification
- 用大模型自动构建最佳最差排序数据，优化情绪分类
- 简化提示+思维链推理使小模型性能媲美大模型
- 公开6类基本情绪数据集，适合情感计算研究者
情绪通过身体体验和生理反应表现，但文本中的具身情绪识别仍研究不足。本文构建了名为CHEER-Ekman的具身情绪分类数据集，扩展了原有二分类具身情绪数据集，涵盖埃克曼提出的六种基本情绪类别。利用大语言模型进行自动最佳最差排序，新方法在该数据集上表现优于传统监督学习。研究发现，简化提示指令与链式思维推理能显著提升情绪识别准确率，使小型模型性能接近大型模型。数据集已公开：https://github.com/menamerai/cheer-ekman。
原文摘要 · Abstract (English)
Emotions manifest through physical experiences and bodily reactions, yet identifying such embodied emotions in text remains understudied. We present an embodied emotion classification dataset, CHEER-Ekman, extending the existing binary embodied emotion dataset with Ekman's six basic emotion categories. Using automatic best-worst scaling with large language models, we achieve performance superior to supervised approaches on our new dataset. Our investigation reveals that simplified prompting instructions and chain-of-thought reasoning significantly improve emotion recognition accuracy, enabling smaller models to achieve competitive performance with larger ones. Our dataset is publicly available at: https://github.com/menamerai/cheer-ekman.
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。