Characterizing Human Explanation Strategies to Inform the Design of Explainable AI for Building Damage Assessment
This work addresses the need for task-specific explainable AI in high-stakes visual detection, though it is incremental as it focuses on understanding human strategies rather than developing new AI methods.
The study investigated human explanation strategies for building damage assessment from satellite imagery to inform explainable AI design, identifying six major strategies through a crowdsourced study with 60 participants.
Explainable AI (XAI) is a promising means of supporting human-AI collaborations for high-stakes visual detection tasks, such as damage detection tasks from satellite imageries, as fully-automated approaches are unlikely to be perfectly safe and reliable. However, most existing XAI techniques are not informed by the understandings of task-specific needs of humans for explanations. Thus, we took a first step toward understanding what forms of XAI humans require in damage detection tasks. We conducted an online crowdsourced study to understand how people explain their own assessments, when evaluating the severity of building damage based on satellite imagery. Through the study with 60 crowdworkers, we surfaced six major strategies that humans utilize to explain their visual damage assessments. We present implications of our findings for the design of XAI methods for such visual detection contexts, and discuss opportunities for future research.