Toward a Dialogue System Using a Large Language Model to Recognize User Emotions with a Camera

TL;DR

This paper explores integrating facial expression-based emotion recognition into large language model dialogue systems to enable AI agents to adapt their responses according to user emotions, enhancing multimodal interaction.

Contribution

It introduces a method for LLM-based AI agents to recognize user emotions from facial expressions via camera and incorporate this information into dialogue prompts.

Findings

AI agents can respond appropriately to emotions like Happy and Angry.

Emotion recognition from facial expressions improves dialogue relevance.

Multimodal emotion-aware dialogue systems are feasible with current LLMs.

Abstract

The performance of ChatGPT\copyright{} and other LLMs has improved tremendously, and in online environments, they are increasingly likely to be used in a wide variety of situations, such as ChatBot on web pages, call center operations using voice interaction, and dialogue functions using agents. In the offline environment, multimodal dialogue functions are also being realized, such as guidance by Artificial Intelligence agents (AI agents) using tablet terminals and dialogue systems in the form of LLMs mounted on robots. In this multimodal dialogue, mutual emotion recognition between the AI and the user will become important. So far, there have been methods for expressing emotions on the part of the AI agent or for recognizing them using textual or voice information of the user's utterances, but methods for AI agents to recognize emotions from the user's facial expressions have not been studied. In this study, we examined whether or not LLM-based AI agents can interact with users according to their emotional states by capturing the user in dialogue with a camera, recognizing emotions from facial expressions, and adding such emotion information to prompts. The results confirmed that AI agents can have conversations according to the emotional state for emotional states with relatively high scores, such as Happy and Angry.