Sentiment-guided Commonsense-aware Response Generation for Mental Health Counseling

2025-01-06

AI Summary

Contemporary virtual psychological assistants suffer from shallow emotion understanding, inadequate empathy, and weak intervention efficacy, failing to address critical barriers to mental health service accessibility—including scarcity of qualified professionals, high costs, and strong stigma. To tackle these challenges, this paper proposes EmpRes, the first framework integrating emotion-oriented and commonsense-aware co-modeling for psychological dialogue. EmpRes pioneers large language model–driven dynamic emotion shaping jointly optimized with commonsense validation. It incorporates the COMET commonsense knowledge graph, fine-grained sentiment polarity detection, and a multi-stage response re-ranking strategy. On the HOPE benchmark, EmpRes comprehensively outperforms state-of-the-art methods. Human evaluation confirms clinical-grade empathic capability, while user studies report 91% perceived effectiveness and 85.45% willingness to continue use and recommend the system.

Technology Category

• Humans and AI: Emotional Intelligence
• Cognitive Modeling & Cognitive Systems: Affective Computing
• Knowledge Representation and Reasoning: Common-Sense Reasoning

Application Category

• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search

Abstract

The crisis of mental health issues is escalating. Effective counseling serves as a critical lifeline for individuals suffering from conditions like PTSD, stress, etc. Therapists forge a crucial therapeutic bond with clients, steering them towards positivity. Unfortunately, the massive shortage of professionals, high costs, and mental health stigma pose significant barriers to consulting therapists. As a substitute, Virtual Mental Health Assistants (VMHAs) have emerged in the digital healthcare space. However, most existing VMHAs lack the commonsense to understand the nuanced sentiments of clients to generate effective responses. To this end, we propose EmpRes, a novel sentiment-guided mechanism incorporating commonsense awareness for generating responses. By leveraging foundation models and harnessing commonsense knowledge, EmpRes aims to generate responses that effectively shape the client's sentiment towards positivity. We evaluate the performance of EmpRes on HOPE, a benchmark counseling dataset, and observe a remarkable performance improvement compared to the existing baselines across a suite of qualitative and quantitative metrics. Moreover, our extensive empirical analysis and human evaluation show that the generation ability of EmpRes is well-suited and, in some cases, surpasses the gold standard. Further, we deploy EmpRes as a chat interface for users seeking mental health support. We address the deployed system's effectiveness through an exhaustive user study with a significant positive response. Our findings show that 91% of users find the system effective, 80% express satisfaction, and over 85.45% convey a willingness to continue using the interface and recommend it to others, demonstrating the practical applicability of EmpRes in addressing the pressing challenges of mental health support, emphasizing user feedback, and ethical considerations in a real-world context.

Problem

• Virtual Psychological Assistants
• Emotional Complexity
• Mental Health Support

Innovation

• EmpRes
• Emotional Understanding
• Virtual Psychological Assistant