Fine-grained Affective Processing Capabilities Emerging from Large Language Models
International Conference on Affective Computing and Intelligent Interaction (ACII), pp. 1–8
Abstract
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.
Authors 6
-
Joost Broekens Aachen
Affiliation as printed
LIACS Leiden University,Leiden,The Netherlands
LIACS Leiden University, Leiden, The Netherlands
-
Bernhard Hilpert Aachen
Affiliation as printed
LIACS Leiden University,Leiden,The Netherlands
LIACS Leiden University, Leiden, The Netherlands
-
Suzan Verberne Aachen
Affiliation as printed
LIACS Leiden University,Leiden,The Netherlands
LIACS Leiden University, Leiden, The Netherlands
-
Affiliation as printed
Free University Amsterdam,Department of Computer Science,Amsterdam,the Netherlands
Department of Computer Science, Free University Amsterdam, Amsterdam, the Netherlands
-
German Research Centre for Artificial Intelligence
Affiliation as printed
German Research Center for Artificial Intelligence (DFKI),Saarbruecken,Germany
German Research Center for Artificial Intelligence (DFKI), Saarbruecken, Germany
-
Aske Plaat Aachen
Affiliation as printed
LIACS Leiden University,Leiden,The Netherlands
LIACS Leiden University, Leiden, The Netherlands
Cited by 26 stored of 27
No patents citing this paper on Lens.org (checked 2026-10-11).