Comparing verbal, visual and combined explanations for Bayesian Network inferences

TL;DR

This study compares verbal, visual, and combined explanation methods for Bayesian Network inferences, showing that multimodal explanations improve user understanding over baseline interfaces.

Contribution

Introduces verbal and visual UI extensions for Bayesian Networks and demonstrates their effectiveness through a user study.

Findings

All explanation types outperform baseline UI in user understanding.

Combined verbal and visual explanations are more effective for certain questions.

Users better understood impact of observations with multimodal explanations.

Abstract

Bayesian Networks (BNs) are an important tool for assisting probabilistic reasoning, but despite being considered transparent models, people have trouble understanding them. Further, current User Interfaces (UIs) still do not clarify the reasoning of BNs. To address this problem, we have designed verbal and visual extensions to the standard BN UI, which can guide users through common inference patterns. We conducted a user study to compare our verbal, visual and combined UI extensions, and a baseline UI. Our main findings are: (1) users did better with all three types of extensions than with the baseline UI for questions about the impact of an observation, the paths that enable this impact, and the way in which an observation influences the impact of other observations; and (2) using verbal and visual modalities together is better than using either modality alone for some of these question types.