Data Therapist: Eliciting Domain Knowledge from Subject Matter Experts Using Large Language Models
This addresses the challenge for domain experts and data analysts in making implicit knowledge explicit to improve data visualization, though it is incremental as it builds on existing mixed-initiative and LLM-based approaches.
The paper tackles the problem of eliciting tacit domain knowledge from subject matter experts for data visualization by introducing the Data Therapist, a web-based system that uses a large language model to prompt users with questions and support annotations, resulting in a structured knowledge base that can inform visualization design, as demonstrated in a qualitative study with experts from three domains.
Effective data visualization requires not only technical proficiency but also a deep understanding of the domain-specific context in which data exists. This context often includes tacit knowledge about data provenance, quality, and intended use, which is rarely explicit in the dataset itself. Motivated by growing demands to surface tacit knowledge, we present the Data Therapist, a web-based system that helps domain experts externalize such implicit knowledge through a mixed-initiative process combining iterative Q&A with interactive annotation. Powered by a large language model, the system automatically analyzes user-supplied datasets, prompts users with targeted questions, and supports annotation at varying levels of granularity. The resulting structured knowledge base can inform both human and automated visualization design. A qualitative study with expert pairs from Accounting, Political Science, and Computer Security revealed recurring patterns in how expert reason about their data and highlighted opportunities for AI support to enhance visualization design.