CauESC: A Causal Aware Model for Emotional Support Conversation

TL;DR

CauESC is a novel model for emotional support conversations that recognizes emotion causes and effects, improving understanding of emotional dynamics and response strategies to better reduce emotional distress.

Contribution

It introduces a framework that identifies emotion causes and effects, and models verbal strategies independently and integratively, advancing emotional support dialogue systems.

Findings

Effective in recognizing emotion causes and effects

Improves understanding of emotional dynamics during conversations

Outperforms existing models on benchmark datasets

Abstract

Emotional Support Conversation aims at reducing the seeker's emotional distress through supportive response. Existing approaches have two limitations: (1) They ignore the emotion causes of the distress, which is important for fine-grained emotion understanding; (2) They focus on the seeker's own mental state rather than the emotional dynamics during interaction between speakers. To address these issues, we propose a novel framework CauESC, which firstly recognizes the emotion causes of the distress, as well as the emotion effects triggered by the causes, and then understands each strategy of verbal grooming independently and integrates them skillfully. Experimental results on the benchmark dataset demonstrate the effectiveness of our approach and show the benefits of emotion understanding from cause to effect and independent-integrated strategy modeling.