arXiv 2606.168432026-06-16cs.CL

基于数据驱动的Russell情感环状模型解码

Data-Driven Decoding of Russell's Circumplex Model of Affect

Alten；CentraleSupélec IETR UMR CNRS 6164（中央理工-高等电力学院 IETR CNRS 6164 联合研究单位）；Inria at Univ. Grenoble Alpes, CNRS, LJK（法国国家信息与自动化研究所，格勒诺布尔阿尔卑斯大学，CNRS，LJK）

Amdjed Belaref, Samir Sadok, Zineb Noumir, Renaud Seguier

备注：: This work has been submitted to the IEEE for possible publication

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文研究Transformer嵌入是否恢复Russell环状模型的几何规律，通过文本和语音模型实验，发现多模态融合完美对齐情感排序，零样本下细粒度情感词接近人类映射坐标。

摘要：

情感计算日益依赖深度学习来表示情感，然而潜在空间通常是不透明的高维黑箱。本文研究Transformer的嵌入是否恢复Russell环状模型的几何规律。我们统一了两个互补实验，检验以下假设：在文本和语音上训练模型后，其潜在空间编码了与效价-唤醒一致的拓扑结构，并再现了类似人类的邻域关系。具体而言，我们评估了基于Transformer的文本（RoBERTa）和语音（wav2vec 2.0）编码器以及多模态Transformer融合架构提取的深度表示，使用了MSP-Podcast等自然数据集和受控的LLM生成刺激。我们的分析表明，文本和音频的多模态融合与Russell的主要情感排序实现了完美的拓扑对齐。此外，在零样本设置中，使用通用文本嵌入，投影的细粒度情感术语接近其已建立的人类映射坐标。我们的贡献是一个新颖的数据驱动框架，用于验证情感模型，证明Russell环状结构内在地编码于这些模态的嵌入中，而不仅仅是人类标注的产物，从而弥合了心理学理论与表示学习之间的差距。

英文摘要：

Affective computing increasingly relies on deep learning to represent emotions, yet latent spaces often remain opaque, high-dimensional black boxes. This paper investigates whether Transformers' embeddings recover the geometric regularities of Russell's circumplex model. We unify two complementary experiments testing the hypothesis that, after training models on text and speech, their resulting latent spaces encode a topology consistent with valence-arousal and reproduce human-like neighborhood relations. Specifically, we evaluate deep representations extracted from Transformer-based text (RoBERTa) and speech (wav2vec 2.0) encoders, along with a multimodal Transformer fusion architecture, across naturalistic datasets like MSP-Podcast and controlled LLM-generated stimuli. Our analysis reveals that multimodal fusion of text and audio yields perfect topological alignment with Russell's primary emotion ordering. Furthermore, in a zero-shot setting using generic text embeddings, projected fine-grained emotion terms fall close to their established human-mapped coordinates. Our contribution is a novel, data-driven framework for validating emotion models, demonstrating that Russell's circumplex structure is intrinsically encoded in the embeddings of these modalities rather than being solely an artifact of human labeling, thereby bridging the gap between psychological theory and representation learning.

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。