SocialSim: Towards Socialized Simulation of Emotional Support Conversation

TL;DR

SocialSim introduces a socialized simulation framework for emotional support conversations, leveraging social dynamics to generate high-quality synthetic data and improve chatbot performance in emotional support tasks.

Contribution

The paper presents SocialSim, a novel framework that incorporates social disclosure and awareness into ESC simulation, creating a large-scale synthetic corpus that surpasses crowdsourced data.

Findings

SSConv outperforms existing datasets in quality.

Chatbot trained on SSConv achieves state-of-the-art results.

SocialSim effectively models social dynamics in ESC.

Abstract

Emotional support conversation (ESC) helps reduce people's psychological stress and provide emotional value through interactive dialogues. Due to the high cost of crowdsourcing a large ESC corpus, recent attempts use large language models for dialogue augmentation. However, existing approaches largely overlook the social dynamics inherent in ESC, leading to less effective simulations. In this paper, we introduce SocialSim, a novel framework that simulates ESC by integrating key aspects of social interactions: social disclosure and social awareness. On the seeker side, we facilitate social disclosure by constructing a comprehensive persona bank that captures diverse and authentic help-seeking scenarios. On the supporter side, we enhance social awareness by eliciting cognitive reasoning to generate logical and supportive responses. Building upon SocialSim, we construct SSConv, a large-scale synthetic ESC corpus of which quality can even surpass crowdsourced ESC data. We further train a chatbot on SSConv and demonstrate its state-of-the-art performance in both automatic and human evaluations. We believe SocialSim offers a scalable way to synthesize ESC, making emotional care more accessible and practical.