Conversational Visual Analytics (CVA)

对话式可视化分析：用户通过与 AI 系统进行多轮自然语言对话来生成、探索和迭代数据可视化，而非直接操作界面。它把 NL2Vis 工具与 LLM 结合，是近年 HCI 和数据可视化研究的活跃方向。

English Definition

"A subfield of visual analytics where users generate, explore, and refine data visualizations through multi-turn natural language dialogue with an AI system, rather than direct manipulation of a UI."

用法说明 · 针对中文母语者

中文常直译为「对话式可视化分析」。CHI、IEEE VIS 上常作为研究主题出现，强调「对话」+「可视化」双通道。

真实用例 · 4 条

"Large Language Models (LLMs) are transforming Conversational Visual Analytics (CVA) by enabling data analysis through natural language."

论文Pipeline extracted — review needed·Abstract 开头点题

"We identified use cases, evaluation criteria and workflows [for CVA]."

论文Pipeline extracted — review needed·描述论文的研究对象

"real-world CVA usage is inherently multi-turn and multi-format"

论文Pipeline extracted — review needed·formative study 结论

"engaged six of the 22 CVA tool developers in a two-week diary study"

论文Pipeline extracted — review needed·用户研究对象招募

由 pipeline 自动采集，待人工 review