Trapp, Anna ORCID: 0009-0008-6992-7644 (2024). Generation of Counterfactual Explanations in Smart Environments. Masters thesis, Universität zu Köln.

[img] PDF
Counterfactual_Explanations_in_Smart_Environments.pdf

Download (3MB)

Abstract

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 human-centered 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.

Item Type: Thesis (Masters thesis)
Creators:
CreatorsEmailORCIDORCID Put Code
Trapp, Annaatrapp.koeln@gmail.comorcid.org/0009-0008-6992-7644UNSPECIFIED
Contributors:
ContributionNameEmail
CensorUNSPECIFIEDUNSPECIFIED
URN: urn:nbn:de:hbz:38-788134
Date: 23 December 2024
Language: English
Faculty: Faculty of Mathematics and Natural Sciences
Divisions: Faculty of Mathematics and Natural Sciences > Department of Mathematics and Computer Science > Institute of Computer Science
Subjects: Data processing Computer science
Uncontrolled Keywords:
KeywordsLanguage
ExplanationEnglish
Explainable SystemsEnglish
Counterfactual ExplanationEnglish
Smart EnvironmentEnglish
Date of oral exam: 10 February 2025
Referee:
NameAcademic Title
Vogelsang, AndreasUNSPECIFIED
Sadeghi, MersedehUNSPECIFIED
Refereed: Yes
URI: http://kups.ub.uni-koeln.de/id/eprint/78813

Downloads

Downloads per month over past year

Export

Actions (login required)

View Item View Item