Avoiding drill-down fallacies with vispilot: Assisted exploration of data subsets

Doris Jung Lin Lee, Himel Dev, Huizi Hu, Hazem Elmeleegy, Aditya Parameswaran

Research output: Contribution to conferencePaper

Abstract

As datasets continue to grow in size and complexity, exploring multidimensional datasets remain challenging for analysts. A common operation during this exploration is drill-downÐunderstanding the behavior of data subsets by progressively adding filters. While widely used, in the absence of careful attention towards confounding factors, drill-downs could lead to inductive fallacies. Specifically, an analyst may end up being łdeceivedž into thinking that a deviation in trend is attributable to a local change, when in fact it is a more general phenomenon; we term this the drill-down fallacy. One way to avoid falling prey to drill-down fallacies is to exhaustively explore all potential drill-down paths, which quickly becomes infeasible on complex datasets with many attributes. We present VisPilot, an accelerated visual data exploration tool that guides analysts through the key insights in a dataset, while avoiding drill-down fallacies. Our user study results show that VisPilot helps analysts discover interesting visualizations, understand attribute importance, and predict unseen visualizations better than other multidimensional data analysis baselines.

Original languageEnglish (US)
Pages186-196
Number of pages11
DOIs
StatePublished - Jan 1 2019
Event24th ACM International Conference on Intelligent User Interfaces, IUI 2019 - Marina del Ray, United States
Duration: Mar 17 2019Mar 20 2019

Conference

Conference24th ACM International Conference on Intelligent User Interfaces, IUI 2019
CountryUnited States
CityMarina del Ray
Period3/17/193/20/19

Keywords

  • Drill-down data analysis
  • Exploratory data analysis
  • Visualization recommendation

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction

Fingerprint Dive into the research topics of 'Avoiding drill-down fallacies with vispilot: Assisted exploration of data subsets'. Together they form a unique fingerprint.

  • Cite this

    Lee, D. J. L., Dev, H., Hu, H., Elmeleegy, H., & Parameswaran, A. (2019). Avoiding drill-down fallacies with vispilot: Assisted exploration of data subsets. 186-196. Paper presented at 24th ACM International Conference on Intelligent User Interfaces, IUI 2019, Marina del Ray, United States. https://doi.org/10.1145/3301275.3302307