Towards an Online Empathetic Chatbot with Emotion Causes
This work addresses the need for more empathetic chatbots in online interactions, focusing on emotion causes rather than just emotion classes, which is an incremental improvement over existing emotion-aware models.
The paper tackled the problem of enabling chatbots to respond empathetically by learning the causes of users' emotions, developing a chatbot that leverages counseling strategies to gather emotion causes in online environments. The result showed effectiveness verified on a real-world online dataset through comparisons with SOTA methods using automatic metrics, expert-based human judgements, and user-based online evaluation.
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.