Abstract
One of the aim of Explainable Artificial Intelligence (XAI) is to equip data-driven, machine-learned models with a high degree of explainability for humans. Understanding and explaining the inferences of a model can be seen as a defeasible reasoning process. This process is likely to be non-monotonic: a conclusion, linked to a set of premises, can be retracted when new information becomes available. In formal logic, computational argumentation is a method, within Artificial Intelligence (AI), focused on modeling defeasible reasoning. This research study focuses on the automatic formation of an argument-based representation for a machine-learned model in order to enhance its degree of explainability, by employing principles and techniques from computational argumentation. It also contributes to the body of knowledge by introducing a novel quantitative human-centred technique to evaluate such a novel representation, and potentially other XAI methods, in the form of a questionnaire for explainability. An experiment have been conducted with two groups of human participants, one interacting with the argument-based representation, and one with a decision trees, a representation deemed naturally transparent and comprehensible. Findings demonstrate that the explainability of the original argument-based representation is statistically similar to that associated to the decision-trees, as reported by humans via the novel questionnaire.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Amgoud, L., Ben-Naim, J.: Ranking-based semantics for argumentation frameworks. In: Liu, W., Subrahmanian, V.S., Wijsen, J. (eds.) SUM 2013. LNCS (LNAI), vol. 8078, pp. 134–147. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-40381-1_11
Baroni, P., Caminada, M., Giacomin, M.: An introduction to argumentation semantics. Knowl. Eng. Rev. 26(4), 365–410 (2011)
Besnard, P., Hunter, A.: A logic-based theory of deductive arguments. Artif. Intell. 128(1–2), 203–235 (2001)
Bryant, D., Krause, P.: A review of current defeasible reasoning implementations. Knowl. Eng. Rev. 23(3), 227–260 (2008)
Choi, B.C., Pak, A.W.: Peer reviewed: a catalog of biases in questionnaires. Prevent Chronic Disease 2(1), 1 (2005)
Cocarascu, O., Toni, F.: Argumentation for machine learning: a survey. In: COMMA, pp. 219–230 (2016)
Dam, H.K., Tran, T., Ghose, A.: Explainable software analytics. In: Proceedings of the 40th International Conference on Software Engineering: New Ideas and Emerging Results, pp. 53–56. ACM, Gothenburg, Sweden (2018)
Dejl, A., et al.: Argflow: a toolkit for deep argumentative explanations for neural networks. In: Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems, pp. 1761–1763 (2021)
Došilović, F.K., Brčić, M., Hlupić, N.: Explainable artificial intelligence: a survey. In: 41st International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), pp. 0210–0215. IEEE (2018)
Dung, P.M.: On the acceptability of arguments and its fundamental role in nonmonotonic reasoning, logic programming and n-person games. Artif. Intell. 77(2), 321–357 (1995)
Freitas, A.A.: Are we really discovering interesting knowledge from data. Expert Update (BCS-SGAI Mag.) 9(1), 41–47 (2006)
Gómez, S.A., Chesnevar, C.I.: Integrating defeasible argumentation and machine learning techniques: a preliminary report. In: Proceedings of Workshop of Researchers in Computer Science, pp. 320–324 (2003)
Gómez, S.A., Chesnevar, C.I.: Integrating defeasible argumentation with fuzzy art neural networks for pattern classification. J. Comput. Sci. Technol. 4(1), 45–51 (2004)
Kriegel, H.P., Kröger, P., Sander, J., Zimek, A.: Density-based clustering. Wiley Interdisc. Rev. Data Mining Knowl. Disc. 1(3), 231–240 (2011)
Lakkaraju, H., Bach, S.H., Leskovec, J.: Interpretable decision sets: a joint framework for description and prediction. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1675–1684. ACM, San Francisco, California, USA (2016)
Lipton, Z.C.: The mythos of model interpretability. Commun. ACM 61(10), 36–43 (2018)
Longo, L.: Argumentation for knowledge representation, conflict resolution, defeasible inference and its integration with machine learning. In: Holzinger, A. (ed.) Machine Learning for Health Informatics. LNCS (LNAI), vol. 9605, pp. 183–208. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-50478-0_9
Longo, L.: Formalising human mental workload as a defeasible computational concept. Ph.D. thesis, Technological University Dublin (2014)
Longo, L., Goebel, R., Lecue, F., Kieseberg, P., Holzinger, A.: Explainable artificial intelligence: concepts, applications, research challenges and visions. In: Holzinger, A., Kieseberg, P., Tjoa, A.M., Weippl, E. (eds.) CD-MAKE 2020. LNCS, vol. 12279, pp. 1–16. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-57321-8_1
Longo, L., Rizzo, L., Dondio, P.: Examining the modelling capabilities of defeasible argumentation and non-monotonic fuzzy reasoning. Knowl. Based Syst. 211, 106514 (2021)
Modgil, S., Prakken, H.: The aspic+ framework for structured argumentation: a tutorial. Argum. Comput. 5(1), 31–62 (2014)
Modgil, S., et al.: The added value of argumentation. In: Ossowski, S. (eds) Agreement Technologies. Law, Governance and Technology Series, vol. 8, pp. 357–403. Springer, Dordrecht (2013). https://doi.org/10.1007/978-94-007-5583-3_21
Riveret, R., Governatori, G.: On learning attacks in probabilistic abstract argumentation. In: Proceedings of the 2016 International Conference on Autonomous Agents and Multiagent Systems, pp. 653–661 (2016)
Rizzo, L., Longo, L.: An empirical evaluation of the inferential capacity of defeasible argumentation, non-monotonic fuzzy reasoning and expert systems. Expert Syst. App. 147, 113220 (2020)
Thimm, M., Kersting, K.: Towards argumentation-based classification. In: Logical Foundations of Uncertainty and Machine Learning, IJCAI Workshop, vol. 17 (2017)
Vilone, G., Longo, L.: Explainable artificial intelligence: a systematic review. arXiv preprint arXiv:2006.00093 (2020)
Vilone, G., Longo, L.: Classification of explainable artificial intelligence methods through their output formats. Mach. Learn. Knowl. Extract. 3(3), 615–661 (2021)
Vilone, G., Longo, L.: Notions of explainability and evaluation approaches for explainable artificial intelligence. Inf. Fusion 76, 89–106 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 IFIP International Federation for Information Processing
About this paper
Cite this paper
Vilone, G., Longo, L. (2022). A Novel Human-Centred Evaluation Approach and an Argument-Based Method for Explainable Artificial Intelligence. In: Maglogiannis, I., Iliadis, L., Macintyre, J., Cortez, P. (eds) Artificial Intelligence Applications and Innovations. AIAI 2022. IFIP Advances in Information and Communication Technology, vol 646. Springer, Cham. https://doi.org/10.1007/978-3-031-08333-4_36
Download citation
DOI: https://doi.org/10.1007/978-3-031-08333-4_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-08332-7
Online ISBN: 978-3-031-08333-4
eBook Packages: Computer ScienceComputer Science (R0)