GenAI for Social Work Field Education: Client Simulation with Real-Time Feedback

2026-01-26

AI Summary

This study addresses the limitations of social work field education, which is often constrained by limited access to qualified supervisors and real clients, as well as the absence of timely and objective feedback mechanisms. To overcome these challenges, the authors propose SWITCH—an interactive training chatbot that integrates a dynamic client profile grounded in cognitive modeling, a fine-tuned BERT-based multi-label counseling skill classifier, and a Motivational Interviewing (MI) stage controller to enable realistic simulation and structured skill development. Experimental results demonstrate that the proposed approach significantly outperforms baseline methods in counseling skill classification accuracy, offering a scalable, low-cost, and consistently reliable intelligent training solution for social work education.

Technology Category

• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Intelligent Robots: Human-Robot Interaction
• Application Domains: Humanities & Computational Social Science

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Field education is the signature pedagogy of social work, yet providing timely and objective feedback during training is constrained by the availability of instructors and counseling clients. In this paper, we present SWITCH, the Social Work Interactive Training Chatbot. SWITCH integrates realistic client simulation, real-time counseling skill classification, and a Motivational Interviewing (MI) progression system into the training workflow. To model a client, SWITCH uses a cognitively grounded profile comprising static fields (e.g., background, beliefs) and dynamic fields (e.g., emotions, automatic thoughts, openness), allowing the agent's behavior to evolve throughout a session realistically. The skill classification module identifies the counseling skills from the user utterances, and feeds the result to the MI controller that regulates the MI stage transitions. To enhance classification accuracy, we study in-context learning with retrieval over annotated transcripts, and a fine-tuned BERT multi-label classifier. In the experiments, we demonstrated that both BERT-based approach and in-context learning outperforms the baseline with big margin. SWITCH thereby offers a scalable, low-cost, and consistent training workflow that complements field education, and allows supervisors to focus on higher-level mentorship.

Problem

• social work education
• client simulation
• real-time feedback
• counseling training
• field education

Innovation

• client simulation
• real-time feedback
• motivational interviewing
• in-context learning
• BERT classifier