{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T09:50:01Z","timestamp":1767261001200,"version":"build-2065373602"},"reference-count":60,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2024,9,12]],"date-time":"2024-09-12T00:00:00Z","timestamp":1726099200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>Explainable Artificial Intelligence (XAI) is a research area that clarifies AI decision-making processes to build user trust and promote responsible AI. Hence, a key scientific challenge in XAI is the development of methods that generate transparent and interpretable explanations while maintaining scalability and effectiveness in complex scenarios. Rule-based methods in XAI generate rules that can potentially explain AI inferences, yet they can also become convoluted in large scenarios, hindering their readability and scalability. Moreover, they often lack contrastive explanations, leaving users uncertain why specific predictions are preferred. To address this scientific problem, we explore the integration of computational argumentation\u2014a sub-field of AI that models reasoning processes through defeasibility\u2014into rule-based XAI systems. Computational argumentation enables arguments modelled from rules to be retracted based on new evidence. This makes it a promising approach to enhancing rule-based methods for creating more explainable AI systems. Nonetheless, research on their integration remains limited despite the appealing properties of rule-based systems and computational argumentation. Therefore, this study also addresses the applied challenge of implementing such an integration within practical AI tools. The study employs the Logic Learning Machine (LLM), a specific rule-extraction technique, and presents a modular design that integrates input rules into a structured argumentation framework using state-of-the-art computational argumentation methods. Experiments conducted on binary classification problems using various datasets from the UCI Machine Learning Repository demonstrate the effectiveness of this integration. The LLM technique excelled in producing a manageable number of if-then rules with a small number of premises while maintaining high inferential capacity for all datasets. In turn, argument-based models achieved comparable results to those derived directly from if-then rules, leveraging a concise set of rules and excelling in explainability. In summary, this paper introduces a novel approach for efficiently and automatically generating arguments and their interactions from data, addressing both scientific and applied challenges in advancing the application and deployment of argumentation systems in XAI.<\/jats:p>","DOI":"10.3390\/make6030101","type":"journal-article","created":{"date-parts":[[2024,9,12]],"date-time":"2024-09-12T11:04:33Z","timestamp":1726139073000},"page":"2049-2073","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["A Novel Integration of Data-Driven Rule Generation and Computational Argumentation for Enhanced Explainable AI"],"prefix":"10.3390","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9805-5306","authenticated-orcid":false,"given":"Lucas","family":"Rizzo","sequence":"first","affiliation":[{"name":"Artificial Intelligence and Cognitive Load Research Lab, School of Computer Science, Technological University Dublin, D07 H6K8 Dublin, Ireland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9912-3454","authenticated-orcid":false,"given":"Damiano","family":"Verda","sequence":"additional","affiliation":[{"name":"Rulex Innovation Labs, Via Felice Romani 9, 16122 Genova, Italy"}]},{"given":"Serena","family":"Berretta","sequence":"additional","affiliation":[{"name":"Rulex Innovation Labs, Via Felice Romani 9, 16122 Genova, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2718-5426","authenticated-orcid":false,"given":"Luca","family":"Longo","sequence":"additional","affiliation":[{"name":"Artificial Intelligence and Cognitive Load Research Lab, School of Computer Science, Technological University Dublin, D07 H6K8 Dublin, Ireland"}]}],"member":"1968","published-online":{"date-parts":[[2024,9,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"101805","DOI":"10.1016\/j.inffus.2023.101805","article-title":"Explainable Artificial Intelligence (XAI): What we know and what is left to attain Trustworthy Artificial Intelligence","volume":"99","author":"Ali","year":"2023","journal-title":"Inf. Fusion"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Markus, A.F., Kors, J.A., and Rijnbeek, P.R. (2021). The role of explainability in creating trustworthy artificial intelligence for health care: A comprehensive survey of the terminology, design choices, and evaluation strategies. J. Biomed. Inform., 113.","DOI":"10.1016\/j.jbi.2020.103655"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"103404","DOI":"10.1016\/j.artint.2020.103404","article-title":"Evaluating XAI: A comparison of rule-based and example-based explanations","volume":"291","author":"Nieuwburg","year":"2021","journal-title":"Artif. Intell."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"120212","DOI":"10.1016\/j.ins.2024.120212","article-title":"Fuzzy inference system with interpretable fuzzy rules: Advancing explainable artificial intelligence for disease diagnosis\u2014A comprehensive review","volume":"662","author":"Cao","year":"2024","journal-title":"Inf. Sci."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"e14","DOI":"10.1017\/S0269888921000102","article-title":"Contrastive explanation: A structural-model approach","volume":"36","author":"Miller","year":"2021","journal-title":"Knowl. Eng. Rev."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/19462166.2013.869764","article-title":"Introduction to structured argumentation","volume":"5","author":"Besnard","year":"2014","journal-title":"Argum. Comput."},{"key":"ref_8","first-page":"25","article-title":"Towards artificial argumentation","volume":"38","author":"Atkinson","year":"2017","journal-title":"AI Mag."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1007\/BF02228999","article-title":"A survey of non-monotonic reasoning","volume":"3","author":"Tompits","year":"1995","journal-title":"Open Syst. Inf. Dyn."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1111\/theo.12405","article-title":"A semantic approach to nonmonotonic reasoning: Inference operations and choice","volume":"88","year":"2022","journal-title":"Theoria"},{"key":"ref_11","unstructured":"Brewka, G. (1991). Nonmonotonic Reasoning: Logical Foundations of Commonsense, Cambridge University Press."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Sklar, E.I., and Azhar, M.Q. (2018;, January 15\u201318). Explanation through Argumentation. Proceedings of the 6th International Conference on Human-Agent Interaction, New York, NY, USA.","DOI":"10.1145\/3284432.3284470"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"e5","DOI":"10.1017\/S0269888921000011","article-title":"Argumentation and explainable artificial intelligence: A survey","volume":"36","author":"Vassiliades","year":"2021","journal-title":"Knowl. Eng. Rev."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"537","DOI":"10.1016\/j.inffus.2022.08.025","article-title":"Comparing and extending the use of defeasible argumentation with quantitative data in real-world contexts","volume":"89","author":"Rizzo","year":"2023","journal-title":"Inf. Fusion"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Vilone, G., and Longo, L. (2021). A Quantitative Evaluation of Global, Rule-Based Explanations of Post-Hoc, Model Agnostic Methods. Front. Artif. Intell., 4.","DOI":"10.3389\/frai.2021.717899"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1109\/TKDE.2009.206","article-title":"Coupling logical analysis of data and shadow clustering for partially defined positive Boolean function reconstruction","volume":"23","author":"Muselli","year":"2009","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"109947","DOI":"10.1016\/j.knosys.2022.109947","article-title":"Greybox XAI: A Neural-Symbolic learning framework to produce interpretable predictions for image classification","volume":"258","author":"Bennetot","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"ref_18","unstructured":"Longo, L. (2023). A Novel Structured Argumentation Framework for Improved Explainability of Classification Tasks. Proceedings of the Explainable Artificial Intelligence, Springer Nature."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Valle, M., Lehmhus, D., Gianoglio, C., Ragusa, E., Seminara, L., Bosse, S., Ibrahim, A., and Thoben, K.D. (2023). A Novel Rule-Based Modeling and Control Approach for the Optimization of Complex Water Distribution Networks. Proceedings of the Advances in System-Integrated Intelligence, Springer International Publishing.","DOI":"10.1007\/978-3-031-16281-7"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"420","DOI":"10.3390\/make6010021","article-title":"Overcoming Therapeutic Inertia in Type 2 Diabetes: Exploring Machine Learning-Based Scenario Simulation for Improving Short-Term Glycemic Control","volume":"6","author":"Nicoletta","year":"2024","journal-title":"Mach. Learn. Knowl. Extr."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1177\/1460458216655188","article-title":"Logic Learning Machine and standard supervised methods for Hodgkin\u2019s lymphoma prognosis using gene expression data and clinical variables","volume":"24","author":"Parodi","year":"2018","journal-title":"Health Inform. J."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Verda, D., Parodi, S., Ferrari, E., and Muselli, M. (2019). Analyzing gene expression data for pediatric and adult cancer diagnosis using logic learning machine and standard supervised methods. BMC Bioinform., 20.","DOI":"10.1186\/s12859-019-2953-8"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Gerussi, A., Verda, D., Cappadona, C., Cristoferi, L., Bernasconi, D.P., Bottaro, S., Carbone, M., Muselli, M., Invernizzi, P., and Asselta, R. (2022). LLM-PBC: Logic Learning Machine-Based Explainable Rules Accurately Stratify the Genetic Risk of Primary Biliary Cholangitis. J. Pers. Med., 12.","DOI":"10.3390\/jpm12101587"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Lindgren, T. (2004). Methods for rule conflict resolution. Proceedings of the European Conference on Machine Learning, Springer.","DOI":"10.1007\/978-3-540-30115-8_26"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Clark, P., and Boswell, R. (1991, January 6\u20138). Rule induction with CN2: Some recent improvements. Proceedings of the Machine Learning\u2014EWSL-91: European Working Session on Learning, Porto, Portugal. Proceedings 5.","DOI":"10.1007\/BFb0017011"},{"key":"ref_26","first-page":"123","article-title":"A Survey of the Role of Voting Mechanisms in Explainable Artificial Intelligence (XAI)","volume":"59","author":"Doe","year":"2022","journal-title":"J. Artif. Intell. Res."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"N\u00f6ssig, A., Hell, T., and Moser, G. (2024). A Voting Approach for Explainable Classification with Rule Learning. Proceedings of the IFIP International Conference on Artificial Intelligence Applications and Innovations, Springer.","DOI":"10.1007\/978-3-031-63223-5_12"},{"key":"ref_28","unstructured":"Lindgren, T., and Bostr\u00f6m, H. (2002, January 24\u201326). Classification with intersecting rules. Proceedings of the Algorithmic Learning Theory: 13th International Conference, ALT 2002, L\u00fcbeck, Germany. Proceedings 13."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"457","DOI":"10.3233\/IDA-2004-8503","article-title":"Resolving rule conflicts with double induction","volume":"8","author":"Lindgren","year":"2004","journal-title":"Intell. Data Anal."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"8721","DOI":"10.1007\/s10462-022-10351-w","article-title":"A survey of Bayesian Network structure learning","volume":"56","author":"Kitson","year":"2023","journal-title":"Artif. Intell. Rev."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"\u010cyras, K., Rago, A., Albini, E., Baroni, P., and Toni, F. (2021). Argumentative XAI: A survey. arXiv.","DOI":"10.24963\/ijcai.2021\/600"},{"key":"ref_32","unstructured":"Espinoza, M.M., Possebom, A.T., and Tacla, C.A. (2019, January 15\u201318). Argumentation-based agents that explain their decisions. Proceedings of the 2019 8th IEEE Brazilian Conference on Intelligent Systems (BRACIS), Salvador, Brazil."},{"key":"ref_33","first-page":"200109","article-title":"Argumentation approaches for explanaible AI in medical informatics","volume":"16","author":"Caroprese","year":"2022","journal-title":"Intell. Syst. Appl."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1093\/logcom\/14.5.675","article-title":"Argumentation semantics for defeasible logic","volume":"14","author":"Governatori","year":"2004","journal-title":"J. Log. Comput."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1016\/j.artint.2007.04.004","article-title":"On principle-based evaluation of extension-based argumentation semantics","volume":"171","author":"Baroni","year":"2007","journal-title":"Artif. Intell."},{"key":"ref_36","first-page":"12","article-title":"A labelling-based justification status of arguments","volume":"3","author":"Wu","year":"2010","journal-title":"Stud. Log."},{"key":"ref_37","first-page":"487","article-title":"Argumentation semantics as formal discussion","volume":"1","author":"Caminada","year":"2017","journal-title":"Handb. Form. Argum."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"100547","DOI":"10.1016\/j.simpa.2023.100547","article-title":"ArgFrame: A multi-layer, web, argument-based framework for quantitative reasoning","volume":"17","author":"Rizzo","year":"2023","journal-title":"Softw. Impacts"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1017\/S0269888911000166","article-title":"An introduction to argumentation semantics","volume":"26","author":"Baroni","year":"2011","journal-title":"Knowl. Eng. Rev."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Longo, L. (2014, January 27\u201329). Defeasible reasoning and argument-based systems in medical fields: An informal overview. Proceedings of the 2014 IEEE 27th International Symposium on Computer-Based Medical Systems, New York, NY, USA.","DOI":"10.1109\/CBMS.2014.126"},{"key":"ref_41","unstructured":"Cocarascu, O., Stylianou, A., \u010cyras, K., and Toni, F. (2020). Data-empowered argumentation for dialectically explainable predictions. ECAI 2020, IOS Press."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Castagna, F., McBurney, P., and Parsons, S. (2024). Explanation\u2013Question\u2013Response dialogue: An argumentative tool for explainable AI. Argum. Comput., 1\u201323. preprint.","DOI":"10.3233\/AAC-230015"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Ferrari, E., and Muselli, M. (2010, January 18\u201323). Maximizing pattern separation in discretizing continuous features for classification purposes. Proceedings of the The 2010 IEEE International Joint Conference on Neural Networks (IJCNN), Barcelona, Spain.","DOI":"10.1109\/IJCNN.2010.5596838"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1471-2105-15-S5-S4","article-title":"Use of Attribute Driven Incremental Discretization and Logic Learning Machine to build a prognostic classifier for neuroblastoma patients","volume":"15","author":"Cangelosi","year":"2014","journal-title":"BMC Bioinform."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Ferrari, E., Verda, D., Pinna, N., and Muselli, M. (2023). Optimizing Water Distribution through Explainable AI and Rule-Based Control. Computers, 12.","DOI":"10.3390\/computers12060123"},{"key":"ref_46","unstructured":"Muselli, M., and Quarati, A. (2005, January 2). Reconstructing positive Boolean functions with shadow clustering. Proceedings of the 2005 IEEE European Conference on Circuit Theory and Design, Cork, Ireland."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Walton, D., Reed, C., and Macagno, F. (2008). Attack, Rebuttal, and Refutation. Argumentation Schemes, Cambridge University Press.","DOI":"10.1017\/CBO9780511802034"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Baumann, R., and Spanring, C. (2017, January 19\u201325). A Study of Unrestricted Abstract Argumentation Frameworks. Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17), Melbourne, Australia.","DOI":"10.24963\/ijcai.2017\/112"},{"key":"ref_49","unstructured":"Dunne, P.E., Hunter, A., McBurney, P., Parsons, S., and Wooldridge, M.J. (2009, January 10\u201315). Inconsistency tolerance in weighted argument systems. Proceedings of the AAMAS (2), Budapest, Hungary."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1016\/j.artint.2010.09.005","article-title":"Weighted argument systems: Basic definitions, algorithms, and complexity results","volume":"175","author":"Dunne","year":"2011","journal-title":"Artif. Intell."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Bistarelli, S., and Santini, F. (2011, January 7\u20139). Conarg: A constraint-based computational framework for argumentation systems. Proceedings of the 2011 IEEE 23rd International Conference on Tools with Artificial Intelligence, Boca Raton, FL, USA.","DOI":"10.1109\/ICTAI.2011.96"},{"key":"ref_52","unstructured":"Pazienza, A., Ferilli, S., Esposito, F., Bistarelli, S., and Giacomin, M. (2017, January 14\u201317). Constructing and Evaluating Bipolar Weighted Argumentation Frameworks for Online Debating Systems. Proceedings of the AI3@ AI* IA, Bari, Italy."},{"key":"ref_53","first-page":"53","article-title":"An Examination of the Effect of the Inconsistency Budget in Weighted Argumentation Frameworks and their Impact on the Interpretation of Deep Neural Networks","volume":"Volume 3554","author":"Longo","year":"2023","journal-title":"Proceedings of the Joint Proceedings of the xAI-2023 Late-breaking Work, Demos and Doctoral Consortium Co-Located with the 1st World Conference on eXplainable Artificial Intelligence (xAI-2023)"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1016\/0004-3702(94)00041-X","article-title":"On the acceptability of arguments and its fundamental role in nonmonotonic reasoning, logic programming and n-person games","volume":"77","author":"Dung","year":"1995","journal-title":"Artif. Intell."},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Bonzon, E., Delobelle, J., Konieczny, S., and Maudet, N. (2016, January 12\u201317). A comparative study of ranking-based semantics for abstract argumentation. Proceedings of the AAAI Conference on Artificial Intelligence, Phoenix, AZ, USA.","DOI":"10.1609\/aaai.v30i1.10116"},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1007\/s11225-009-9218-x","article-title":"A logical account of formal argumentation","volume":"93","author":"Caminada","year":"2009","journal-title":"Stud. Log."},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Caminada, M. (2006). On the issue of reinstatement in argumentation. Proceedings of the European Workshop on Logics in Artificial Intelligence, Springer.","DOI":"10.1007\/11853886_11"},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1016\/S0004-3702(01)00071-6","article-title":"A logic-based theory of deductive arguments","volume":"128","author":"Besnard","year":"2001","journal-title":"Artif. Intell."},{"key":"ref_59","unstructured":"Longo, L. (2023). Development of a Human-Centred Psychometric Test for the Evaluation of Explanations Produced by XAI Methods. Proceedings of the Explainable Artificial Intelligence, Springer Nature."},{"key":"ref_60","doi-asserted-by":"crossref","unstructured":"Lv, G., Chen, L., and Cao, C.C. (2022). On glocal explainability of graph neural networks. Proceedings of the International Conference on Database Systems for Advanced Applications, Springer.","DOI":"10.1007\/978-3-031-00123-9_52"}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/6\/3\/101\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T15:55:06Z","timestamp":1760111706000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/6\/3\/101"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,12]]},"references-count":60,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,9]]}},"alternative-id":["make6030101"],"URL":"https:\/\/doi.org\/10.3390\/make6030101","relation":{},"ISSN":["2504-4990"],"issn-type":[{"type":"electronic","value":"2504-4990"}],"subject":[],"published":{"date-parts":[[2024,9,12]]}}}