Causal Perception in Question-Answering Systems

TL;DR

This paper investigates how question-answering systems influence user perceptions of causality, revealing that certain visualizations and warnings can affect the acceptance of causal claims and reduce misconceptions.

Contribution

It provides empirical evidence on how visual and textual cues in QA systems impact causal reasoning and proposes methods to mitigate causal illusions.

Findings

Scatterplots increase plausibility of unreasonable causal claims.

Warnings about correlation and causation influence user acceptance.

Users tend to confuse correlation with causation, but warnings can reduce this bias.

Abstract

Root cause analysis is a common data analysis task. While question-answering systems enable people to easily articulate a why question (e.g., why students in Massachusetts have high ACT Math scores on average) and obtain an answer, these systems often produce questionable causal claims. To investigate how such claims might mislead users, we conducted two crowdsourced experiments to study the impact of showing different information on user perceptions of a question-answering system. We found that in a system that occasionally provided unreasonable responses, showing a scatterplot increased the plausibility of unreasonable causal claims. Also, simply warning participants that correlation is not causation seemed to lead participants to accept reasonable causal claims more cautiously. We observed a strong tendency among participants to associate correlation with causation. Yet, the warning appeared to reduce the tendency. Grounded in the findings, we propose ways to reduce the illusion of causality when using question-answering systems.