What is understandable in Bayesian network explanations?
Artificial Intelligence
2021-10-05 v1
Abstract
Explaining predictions from Bayesian networks, for example to physicians, is non-trivial. Various explanation methods for Bayesian network inference have appeared in literature, focusing on different aspects of the underlying reasoning. While there has been a lot of technical research, there is very little known about how well humans actually understand these explanations. In this paper, we present ongoing research in which four different explanation approaches were compared through a survey by asking a group of human participants to interpret the explanations.
Cite
@article{arxiv.2110.01322,
title = {What is understandable in Bayesian network explanations?},
author = {Raphaela Butz and Renée Schulz and Arjen Hommersom and Marko van Eekelen},
journal= {arXiv preprint arXiv:2110.01322},
year = {2021}
}