Chat-Capsule: A Hierarchical Capsule for Dialog-level Emotion Analysis
This work addresses the need for dialog-level emotion detection in applications like customer support, where fine-grained annotations such as user satisfaction and emotion curves are crucial, though it appears incremental by extending existing capsule methods to a hierarchical structure.
The authors tackled the problem of dialog-level emotion analysis by proposing a hierarchical capsule model that captures both utterance-level and dialog-level emotions and their interrelations, achieving state-of-the-art performance on benchmark and proprietary datasets.
Many studies on dialog emotion analysis focus on utterance-level emotion only. These models hence are not optimized for dialog-level emotion detection, i.e. to predict the emotion category of a dialog as a whole. More importantly, these models cannot benefit from the context provided by the whole dialog. In real-world applications, annotations to dialog could fine-grained, including both utterance-level tags (e.g. speaker type, intent category, and emotion category), and dialog-level tags (e.g. user satisfaction, and emotion curve category). In this paper, we propose a Context-based Hierarchical Attention Capsule~(Chat-Capsule) model, which models both utterance-level and dialog-level emotions and their interrelations. On a dialog dataset collected from customer support of an e-commerce platform, our model is also able to predict user satisfaction and emotion curve category. Emotion curve refers to the change of emotions along the development of a conversation. Experiments show that the proposed Chat-Capsule outperform state-of-the-art baselines on both benchmark dataset and proprietary dataset. Source code will be released upon acceptance.