Plausible Counterfactual Explanations of Recommendations

TL;DR

This paper introduces a method for generating highly plausible counterfactual explanations in recommender systems, enhancing transparency and user trust, validated through numerical analysis and user studies.

Contribution

The paper proposes a novel approach for producing plausible counterfactual explanations specifically tailored for recommender systems, addressing a gap in explanation quality.

Findings

The method produces highly plausible counterfactual explanations.

Numerical evaluations show improved explanation plausibility.

User studies confirm increased user trust and understanding.

Abstract

Explanations play a variety of roles in various recommender systems, from a legally mandated afterthought, through an integral element of user experience, to a key to persuasiveness. A natural and useful form of an explanation is the Counterfactual Explanation (CE). We present a method for generating highly plausible CEs in recommender systems and evaluate it both numerically and with a user study.