Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Jing Bian, Haoxiang Su, Liting Jiang, Di Wu, Ruiyu Fang, Xiaomeng Huang, Yanbing Li, Shuangyong Song, Hao Huang

TL;DR

A multi-task, multi-label Chinese dialogue dataset is constructed 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.

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.

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

TL;DR

A multi-task, multi-label Chinese dialogue dataset is constructed 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.

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.
Paper Structure (10 sections, 2 figures, 4 tables)

This paper contains 10 sections, 2 figures, 4 tables.

Table of Contents

  1. Introduction
  2. RELATED WORK
  3. DATASET CONSTRUCTION
  4. Data Collection
  5. Annotate Details And Consistency
  6. Experimental
  7. Experimental Setup
  8. Baselines
  9. Experimental Analysis
  10. Conclusion

Figures (2)

  • Figure 1: An example from the dataset. The green box represents the customer service representative, and the yellow box represents the user. The user's initial emotional state transition is empty. We annotate each user's utterance with emotion, emotional state transition, and satisfaction.
  • Figure 2: Model architecture diagram. Blue boxes represent the emotion recognition task, yellow boxes represent the emotion state transition task, and green boxes represent the satisfaction prediction task.