Large language models, in particular generative pre-trained transformers
(GPTs), show impressive results on a wide variety of language-related tasks. In
this paper, we explore ChatGPT's zero-shot ability to perform affective
computing tasks using prompting alone. We show that ChatGPT a) performs
meaningful sentiment analysis in the Valence, Arousal and Dominance dimensions,
b) has meaningful emotion representations in terms of emotion categories and
these affective dimensions, and c) can perform basic appraisal-based emotion
elicitation of situations based on a prompt-based computational implementation
of the OCC appraisal model. These findings are highly relevant: First, they
show that the ability to solve complex affect processing tasks emerges from
language-based token prediction trained on extensive data sets. Second, they
show the potential of large language models for simulating, processing and
analyzing human emotions, which has important implications for various
applications such as sentiment analysis, socially interactive agents, and
social robotics.

本文研究了大型语言模型（尤其是生成预训练变压器）在各种语言相关任务上显示出的令人印象深刻的结果。我们探索了 ChatGPT 仅通过提示就能够执行情感计算任务的零点能力。我们显示 ChatGPT a）能够在价值、唤起和支配维度上执行有意义的情绪分析，b）在情绪类别和这些情感维度方面具有有意义的情感表示，以及 c）可以根据基于提示的 OCC 评估模型的计算实现，对情况进行基本的评估引发情绪的操作。这些发现具有很高的相关性：首先，它们表明解决复杂的情感处理任务的能力源于对广泛数据集进行基于语言的标记预测的训练。其次，它们显示了大型语言模型模拟、处理和分析人类情绪的潜力，这对于诸如情感分析、社交互动代理和社交机器人等各种应用具有重要意义。