Abstract
Natural Language Interfaces to Databases (NLIDBs) provide a promising approach to lower barriers for non-technical users to access data by generating SQL queries from natural language input. However, non-technical users typically lack the skills to assess whether generated queries align with their intent. This paper introduces a MiXQL, a novel multimodal SQL explanation system designed to enhance query comprehension for non-technical users. Grounded in design science research, we propose four design principles and instantiated them in a prototype and evaluated it in a pilot study (N=20). Results indicate that while comprehension benefits are limited for simple queries, multimodal explanations substantially improve understanding of complex SQL constructs such as joins, aggregations, and subqueries. These findings highlight the potential of explanation mechanisms to improve transparency and support data democratization within organizations.
Recommended Citation
Schelhorn, Till; Hohenloechter, Lukas; and Maedche, Alexander, "MiXQL – A Multimodal SQL Explanation System for Query Comprehension: Results of a Pilot Study" (2025). SIGHCI 2025 Proceedings. 14.
https://aisel.aisnet.org/sighci2025/14