Applying Attribution Explanations in Truth-Discovery Quantitative Bipolar Argumentation Frameworks

TL;DR

This paper explores the application of attribution explanations, specifically AAEs and RAEs, to cyclic QBAFs in truth discovery, revealing their usefulness in providing insightful explanations for complex argumentation structures.

Contribution

It extends the use of attribution explanations to cyclic QBAFs in truth discovery, comparing AAEs and RAEs in complex, real-world scenarios.

Findings

Both AAEs and RAEs offer valuable explanations.

They provide non-trivial, surprising insights.

Applications to cyclic QBAFs are feasible and insightful.

Abstract

Explaining the strength of arguments under gradual semantics is receiving increasing attention. For example, various studies in the literature offer explanations by computing the attribution scores of arguments or edges in Quantitative Bipolar Argumentation Frameworks (QBAFs). These explanations, known as Argument Attribution Explanations (AAEs) and Relation Attribution Explanations (RAEs), commonly employ removal-based and Shapley-based techniques for computing the attribution scores. While AAEs and RAEs have proven useful in several applications with acyclic QBAFs, they remain largely unexplored for cyclic QBAFs. Furthermore, existing applications tend to focus solely on either AAEs or RAEs, but do not compare them directly. In this paper, we apply both AAEs and RAEs, to Truth Discovery QBAFs (TD-QBAFs), which assess the trustworthiness of sources (e.g., websites) and their claims (e.g., the severity of a virus), and feature complex cycles. We find that both AAEs and RAEs can provide interesting explanations and can give non-trivial and surprising insights.