A benchmark for joint dialogue satisfaction, emotion recognition, and emotion state transition prediction

TL;DR

This paper introduces a new Chinese dialogue dataset designed for multi-task learning of satisfaction, emotion recognition, and emotional state transition, addressing limitations of existing datasets and capturing dynamic emotional changes across dialogue turns.

Contribution

It presents a novel multi-task, multi-label Chinese dialogue dataset supporting satisfaction and emotion analysis, enabling more comprehensive emotion and satisfaction modeling in dialogue systems.

Findings

Dataset supports multi-task learning for satisfaction and emotion recognition

Captures emotional state transitions across dialogue turns

Provides new resources for emotion and satisfaction research in dialogue systems

Abstract

User satisfaction is closely related to enterprises, as it not only directly reflects users' subjective evaluation of service quality or products, but also affects customer loyalty and long-term business revenue. Monitoring and understanding user emotions during interactions helps predict and improve satisfaction. However, relevant Chinese datasets are limited, and user emotions are dynamic; relying on single-turn dialogue cannot fully track emotional changes across multiple turns, which may affect satisfaction prediction. To address this, we constructed a multi-task, multi-label Chinese dialogue dataset that supports satisfaction recognition, as well as emotion recognition and emotional state transition prediction, providing new resources for studying emotion and satisfaction in dialogue systems.