More Than Accuracy: Towards Trustworthy Machine Learning Interfaces for Object Recognition
This addresses the problem of user trust in ML interfaces for object recognition, particularly for users with ML backgrounds, but it is incremental as it builds on existing visualization studies.
The paper investigates how visualizations of object recognition ML systems affect user trust and reliance, finding that users consider factors beyond accuracy, such as the plausibility and severity of errors, and prefer seeing prediction probabilities.
This paper investigates the user experience of visualizations of a machine learning (ML) system that recognizes objects in images. This is important since even good systems can fail in unexpected ways as misclassifications on photo-sharing websites showed. In our study, we exposed users with a background in ML to three visualizations of three systems with different levels of accuracy. In interviews, we explored how the visualization helped users assess the accuracy of systems in use and how the visualization and the accuracy of the system affected trust and reliance. We found that participants do not only focus on accuracy when assessing ML systems. They also take the perceived plausibility and severity of misclassification into account and prefer seeing the probability of predictions. Semantically plausible errors are judged as less severe than errors that are implausible, which means that system accuracy could be communicated through the types of errors.