Applying attribution explanations in truth-discovery quantitative bipolar argumentation frameworks
File(s)
Published version
Author(s)
Yin, Xiang
Potyka, nico
Toni, francesca
Type
Conference Paper
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.
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.
Date Issued
2024-09-28
Date Acceptance
2024-08-12
Citation
CEUR Workshop Proceedings, 2024, pp.56-66
ISSN
1613-0073
Publisher
CEUR Workshop Proceedings
Start Page
56
End Page
66
Journal / Book Title
CEUR Workshop Proceedings
Copyright Statement
© 2024 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0)
License URL
Source
2nd International Workshop on Argumentation for eXplainable AI (ArgXAI) co-located with 10th International Conference on Computational Models of Argument (COMMA 2024)
Subjects
Explainable AI
Quantitative Argumentation
Truth Discovery Application
Publication Status
Published
Start Date
2024-09-16
Coverage Spatial
Hagen, Germany
Rights Embargo Date
10000-01-01