Comparing verbal, visual and combined explanations for Bayesian Network inferences
This work addresses usability issues in probabilistic reasoning tools for users, but it is incremental as it builds on existing UI designs with specific extensions.
The paper tackled the problem of users struggling to understand Bayesian Network inferences by designing verbal and visual UI extensions, finding that all extensions improved user performance over a baseline, with combined modalities outperforming single ones for certain question types.
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.