Explainable and argumentation-based decision making with qualitative preferences for diagnostics and prognostics of Alzheimer's Disease

Argumentation has gained traction as a formalism to make more transparent decisions and provide formal explanations recently. In this paper, we present an argumentation-based approach to decision making that can support modelling and automated reasoning about complex qualitative preferences and offe...

Full description

Bibliographic Details
Main Authors: Zeng, Zhiwei, Shen, Zhiqi, Tan, Benny Toh Hsiang, Chin, Jing Jih, Leung, Cyril, Wang, Yu, Chi, Ying, Miao, Chunyan
Other Authors: School of Computer Science and Engineering
Format: Conference Paper
Language:English
Published: 2021
Subjects:
Online Access:https://hdl.handle.net/10356/148710
_version_ 1826125891226304512
author Zeng, Zhiwei
Shen, Zhiqi
Tan, Benny Toh Hsiang
Chin, Jing Jih
Leung, Cyril
Wang, Yu
Chi, Ying
Miao, Chunyan
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Zeng, Zhiwei
Shen, Zhiqi
Tan, Benny Toh Hsiang
Chin, Jing Jih
Leung, Cyril
Wang, Yu
Chi, Ying
Miao, Chunyan
author_sort Zeng, Zhiwei
collection NTU
description Argumentation has gained traction as a formalism to make more transparent decisions and provide formal explanations recently. In this paper, we present an argumentation-based approach to decision making that can support modelling and automated reasoning about complex qualitative preferences and offer dialogical explanations for the decisions made. We first propose Qualitative Preference Decision Frameworks (QPDFs). In a QPDF, we use contextual priority to represent the relative importance of combinations of goals in different contexts and define associated strategies for deriving decision preferences based on prioritized goal combinations. To automate the decision computation, we map QPDFs to Assumption-based Argumentation (ABA) frameworks so that we can utilize existing ABA argumentative engines for our implementation. We implemented our approach for two tasks, diagnostics and prognostics of Alzheimer's Disease (AD), and evaluated it with real-world datasets. For each task, one of our models achieves the highest accuracy and good precision and recall for all classes compared to common machine learning models. Moreover, we study how to formalize argumentation dialogues that give contrastive, focused and selected explanations for the most preferred decisions selected in given contexts.
first_indexed 2024-10-01T06:43:48Z
format Conference Paper
id ntu-10356/148710
institution Nanyang Technological University
language English
last_indexed 2024-10-01T06:43:48Z
publishDate 2021
record_format dspace
spelling ntu-10356/1487102021-05-28T03:10:15Z Explainable and argumentation-based decision making with qualitative preferences for diagnostics and prognostics of Alzheimer's Disease Zeng, Zhiwei Shen, Zhiqi Tan, Benny Toh Hsiang Chin, Jing Jih Leung, Cyril Wang, Yu Chi, Ying Miao, Chunyan School of Computer Science and Engineering International Conference on Principles of Knowledge Representation and Reasoning (KR'20) Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly (LILY) Engineering Development Deployment Argumentation has gained traction as a formalism to make more transparent decisions and provide formal explanations recently. In this paper, we present an argumentation-based approach to decision making that can support modelling and automated reasoning about complex qualitative preferences and offer dialogical explanations for the decisions made. We first propose Qualitative Preference Decision Frameworks (QPDFs). In a QPDF, we use contextual priority to represent the relative importance of combinations of goals in different contexts and define associated strategies for deriving decision preferences based on prioritized goal combinations. To automate the decision computation, we map QPDFs to Assumption-based Argumentation (ABA) frameworks so that we can utilize existing ABA argumentative engines for our implementation. We implemented our approach for two tasks, diagnostics and prognostics of Alzheimer's Disease (AD), and evaluated it with real-world datasets. For each task, one of our models achieves the highest accuracy and good precision and recall for all classes compared to common machine learning models. Moreover, we study how to formalize argumentation dialogues that give contrastive, focused and selected explanations for the most preferred decisions selected in given contexts. AI Singapore Accepted version 2021-05-28T03:07:23Z 2021-05-28T03:07:23Z 2020 Conference Paper Zeng, Z., Shen, Z., Tan, B. T. H., Chin, J. J., Leung, C., Wang, Y., Chi, Y. & Miao, C. (2020). Explainable and argumentation-based decision making with qualitative preferences for diagnostics and prognostics of Alzheimer's Disease. International Conference on Principles of Knowledge Representation and Reasoning (KR'20), 816-826. https://dx.doi.org/10.24963/kr.2020/84 978-0-9992411-7-2 https://hdl.handle.net/10356/148710 10.24963/kr.2020/84 816 826 en © 2020 International Joint Conferences on Artificial Intelligence Organization. All rights reserved. This paper was published in International Conference on Principles of Knowledge Representation and Reasoning (KR'20) and is made available with permission of International Joint Conferences on Artificial Intelligence Organization application/pdf
spellingShingle Engineering
Development
Deployment
Zeng, Zhiwei
Shen, Zhiqi
Tan, Benny Toh Hsiang
Chin, Jing Jih
Leung, Cyril
Wang, Yu
Chi, Ying
Miao, Chunyan
Explainable and argumentation-based decision making with qualitative preferences for diagnostics and prognostics of Alzheimer's Disease
title Explainable and argumentation-based decision making with qualitative preferences for diagnostics and prognostics of Alzheimer's Disease
title_full Explainable and argumentation-based decision making with qualitative preferences for diagnostics and prognostics of Alzheimer's Disease
title_fullStr Explainable and argumentation-based decision making with qualitative preferences for diagnostics and prognostics of Alzheimer's Disease
title_full_unstemmed Explainable and argumentation-based decision making with qualitative preferences for diagnostics and prognostics of Alzheimer's Disease
title_short Explainable and argumentation-based decision making with qualitative preferences for diagnostics and prognostics of Alzheimer's Disease
title_sort explainable and argumentation based decision making with qualitative preferences for diagnostics and prognostics of alzheimer s disease
topic Engineering
Development
Deployment
url https://hdl.handle.net/10356/148710
work_keys_str_mv AT zengzhiwei explainableandargumentationbaseddecisionmakingwithqualitativepreferencesfordiagnosticsandprognosticsofalzheimersdisease
AT shenzhiqi explainableandargumentationbaseddecisionmakingwithqualitativepreferencesfordiagnosticsandprognosticsofalzheimersdisease
AT tanbennytohhsiang explainableandargumentationbaseddecisionmakingwithqualitativepreferencesfordiagnosticsandprognosticsofalzheimersdisease
AT chinjingjih explainableandargumentationbaseddecisionmakingwithqualitativepreferencesfordiagnosticsandprognosticsofalzheimersdisease
AT leungcyril explainableandargumentationbaseddecisionmakingwithqualitativepreferencesfordiagnosticsandprognosticsofalzheimersdisease
AT wangyu explainableandargumentationbaseddecisionmakingwithqualitativepreferencesfordiagnosticsandprognosticsofalzheimersdisease
AT chiying explainableandargumentationbaseddecisionmakingwithqualitativepreferencesfordiagnosticsandprognosticsofalzheimersdisease
AT miaochunyan explainableandargumentationbaseddecisionmakingwithqualitativepreferencesfordiagnosticsandprognosticsofalzheimersdisease