Chat-Capsule: A Hierarchical Capsule for Dialog-level Emotion Analysis

Abstract

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 finegrained, 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 stateof-the-art baselines on both benchmark dataset and proprietary dataset. Source code will be released upon acceptance.

FADO: Feedback-Aware Double COntrolling Network for Emotional Support Conversation

“…A critical research problem for dialog systems is to design agents that have emotional intelligence [18], which is defined as the ability to perceive, integrate, understand, and regulate emotions [22]. Recently, reseraches on emotional chatting have grown rapidly [34,26,31,6,29]. The notable work [34], Emotional Chatting Machine (ECM), gener-ates appropriate emotional responses conditioning on a prespecified label with memory network [14].…”