From Facts to Foils: Designing and Evaluating Counterfactual Explanations for Smart Environments
This work addresses the need for explainability in smart environments by providing a practical framework for counterfactual explanations, though it is incremental as it builds on existing explanation engines.
The paper tackled the lack of established methods for generating counterfactual explanations in rule-based smart environments by formalizing and implementing the first tailored approach, with a user study (N=17) showing that user preference depends on context, with causal explanations favored for simplicity and time pressure, and counterfactuals preferred for actionable problem-solving.
Explainability is increasingly seen as an essential feature of rule-based smart environments. While counterfactual explanations, which describe what could have been done differently to achieve a desired outcome, are a powerful tool in eXplainable AI (XAI), no established methods exist for generating them in these rule-based domains. In this paper, we present the first formalization and implementation of counterfactual explanations tailored to this domain. It is implemented as a plugin that extends an existing explanation engine for smart environments. We conducted a user study (N=17) to evaluate our generated counterfactuals against traditional causal explanations. The results show that user preference is highly contextual: causal explanations are favored for their linguistic simplicity and in time-pressured situations, while counterfactuals are preferred for their actionable content, particularly when a user wants to resolve a problem. Our work contributes a practical framework for a new type of explanation in smart environments and provides empirical evidence to guide the choice of when each explanation type is most effective.