Evaluative Item-Contrastive Explanations in Rankings
This work addresses the need for interpretability in ranking systems, which are important in various domains, but it appears incremental as it adapts existing contrastive explanation methods to a specific context.
The paper tackles the problem of explaining ranking systems by introducing Evaluative Item-Contrastive Explanations, which combine contrastive explanations with an evaluative methodology to assess positive and negative aspects, and demonstrates its application through an experiment on public data.
The remarkable success of Artificial Intelligence in advancing automated decision-making is evident both in academia and industry. Within the plethora of applications, ranking systems hold significant importance in various domains. This paper advocates for the application of a specific form of Explainable AI -- namely, contrastive explanations -- as particularly well-suited for addressing ranking problems. This approach is especially potent when combined with an Evaluative AI methodology, which conscientiously evaluates both positive and negative aspects influencing a potential ranking. Therefore, the present work introduces Evaluative Item-Contrastive Explanations tailored for ranking systems and illustrates its application and characteristics through an experiment conducted on publicly available data.