Conveying Causality through Visualization: A Survey of Visual Causal Inference

Authors

Arran Zeyu Wang (University of North Carolina-Chapel Hill), David Borland (University of North Carolina at Chapel Hill), David Gotz (University of North Carolina)

Presentation

Session
I don't trust you, explain yourself!
Time
Friday, Nov 13, 08:00 – 08:12 (US/Eastern) · session 08:00 – 09:30
Location
Hall Essex north

Keywords

Visual Causal Inference, Data Visualization, Exploratory Data Analysis, Causality, Decision Making, Literature Review

Abstract

While data visualization has historically focused on revealing frequencies, correlations, and other descriptive patterns, relying on descriptive statistics alone during exploratory data analysis may lead to spurious conclusions. Consequently, Visual Causal Inference (VCI) has emerged as a critical research topic, combining data visualization, an understanding of human perception and cognition, human-computer interaction, and the rigor of statistical causal inference and modeling. Reflecting the broad applicability of such work, the literature surrounding VCI has addressed a variety of research questions, fragmented across different contribution types, venues, and application domains. This paper provides the first systematic review of the VCI landscape and proposes a taxonomy for structuring the domain across three core categories: the Structural Pillar, examining interactive visual analytics techniques with a graphical structure presenting causal structures; the Augmentative Pillar, exploring techniques to estimate causal effects using auxiliary representations; and the Cognitive Pillar, studying how humans perceive and comprehend causality from visualizations. By synthesizing these areas, we map the current design space and identify critical gaps and emerging opportunities in VCI, calling for future actions in unifying the pillars, navigating design trade-offs, and bridging the evaluation gap for better visual communication of causality.

For Practitioners

analysts, data scientists