Data Therapist: Eliciting Domain Knowledge from Subject Matter Experts Using Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908621748568064 |
|---|---|
| author | Shin, Sungbok Jeon, Hyeon Hong, Sanghyun Elmqvist, Niklas |
| author_facet | Shin, Sungbok Jeon, Hyeon Hong, Sanghyun Elmqvist, Niklas |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_00455 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Data Therapist: Eliciting Domain Knowledge from Subject Matter Experts Using Large Language Models Shin, Sungbok Jeon, Hyeon Hong, Sanghyun Elmqvist, Niklas Human-Computer Interaction Artificial Intelligence 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. |
| title | Data Therapist: Eliciting Domain Knowledge from Subject Matter Experts Using Large Language Models |
| topic | Human-Computer Interaction Artificial Intelligence |
| url | https://arxiv.org/abs/2505.00455 |