Signal Adapting from Downturns: Prediction of Long-Term Conversational-Skill Development in Mental-Health Crisis Counselors

Summary

How people learn to become better conversationalists is especially important in mental-health counseling, where conversational skills are essential yet volunteer counselors often have limited access to supervision and structured feedback. The researchers introduce the task of predicting, early in a conversationalist's career, whether they will eventually improve at steering conversations toward positive outcomes, and demonstrate the feasibility of this task for volunteer mental-health crisis counselors. Their central insight is that people may struggle with particular kinds of moments in a conversation, and that how they learn to handle those moments over time is especially revealing of their likelihood of future improvement. They operationalize this by identifying the types of moments a counselor initially struggles with, capturing how they adapt their response when re-encountering similar moments in subsequent conversations, and learning which early adaptations predict improvement months or even years later. While this future-prediction task is challenging, the counselor-adaptation approach yields better results than baselines that learn directly from the conversation transcript.