Towards an Online Empathetic Chatbot with Emotion Causes

Abstract

Existing emotion-aware conversational models usually focus on controlling the response contents to align with a specific emotion class, whereas empathy is the ability to understand and concern the feelings and experience of others. Hence, it is critical to learn the causes that evoke the users' emotion for empathetic responding, a.k.a. emotion causes. To gather emotion causes in online environments, we leverage counseling strategies and develop an empathetic chatbot to utilize the causal emotion information. On a real-world online dataset, we verify the effectiveness of the proposed approach by comparing our chatbot with several SOTA methods using automatic metrics, expert-based human judgements as well as user-based online evaluation.

arXiv commentSIGIR 2021

References in corpus (4)

• Unified Language Model Pre-training for Natural Language Understanding and Generation
• TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents
• An Empirical Investigation of Pre-Trained Transformer Language Models for Open-Domain Dialogue Generation
• A Syntactically Constrained Bidirectional-Asynchronous Approach for Emotional Conversation Generation

Cited by in corpus (4)

• Empathetic Conversational Systems: A Review of Current Advances, Gaps, and Opportunities
• ChaCha: Leveraging Large Language Models to Prompt Children to Share Their Emotions about Personal Events
• "You tell me": A Dataset of GPT-4-Based Behaviour Change Support Conversations
• Generative Emotion Cause Explanation in Multimodal Conversations