FactExplorer: Fact Embedding-Based Exploratory Data Analysis for Tabular Data

Despite exploratory data analysis (EDA) is a powerful approach for uncovering insights from unfamiliar datasets, existing EDA tools face challenges in assisting users to assess the progress of exploration and synthesize coherent insights from isolated findings. To address these challenges, we present FactExplorer, a novel fact-based EDA system that shifts the analysis focus from raw data to data facts. FactExplorer employs a hybrid logical-visual representation, providing users with a comprehensive overview of all potential facts at the outset of their exploration. Moreover, FactExplorer introduces fact-mining techniques, including topic-based drill-down and transition path search capabilities. These features facilitate in-depth analysis of facts and enhance the understanding of interconnections between specific facts. Finally, we present a usage scenario and conduct a user study to assess the effectiveness of FactExplorer. The results indicate that FactExplorer facilitates the understanding of isolated findings and enables users to steer a thorough and effective EDA.

尽管探索性数据分析（Exploratory Data Analysis，EDA）是从陌生数据集中挖掘潜在洞见的有效途径，但现有EDA工具仍存在两大局限：一是难以辅助用户评估探索进程，二是无法帮助用户从零散的研究发现中整合出连贯的系统性洞见。为解决上述挑战，我们提出了FactExplorer——一款基于事实的新型EDA系统，将分析核心从原始数据转向数据事实本身。FactExplorer采用混合逻辑-可视化表征方案，可让用户在探索初期便能全面掌握所有潜在数据事实的整体概览。此外，FactExplorer集成了事实挖掘技术，涵盖基于主题的下钻分析与跳转路径搜索功能，这些特性可助力用户对数据事实展开深入剖析，并强化其对特定事实间内在关联的认知。最后，我们通过展示一个典型使用场景并开展用户研究，对FactExplorer的实际效能进行了评估。实验结果表明，FactExplorer可有效帮助用户理解零散的研究发现，并支持用户开展全面且高效的探索性数据分析工作。