{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T03:43:29Z","timestamp":1777434209447,"version":"3.51.4"},"reference-count":46,"publisher":"SAGE Publications","issue":"2","license":[{"start":{"date-parts":[[2021,4,26]],"date-time":"2021-04-26T00:00:00Z","timestamp":1619395200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Argument &amp; Computation"],"published-print":{"date-parts":[[2022,6,1]]},"abstract":"<jats:p>This paper proposes a formal top-level model of explaining the outputs of machine-learning-based decision-making applications and evaluates it experimentally with three data sets. The model draws on AI &amp; law research on argumentation with cases, which models how lawyers draw analogies to past cases and discuss their relevant similarities and differences in terms of relevant factors and dimensions in the problem domain. A case-based approach is natural since the input data of machine-learning applications can be seen as cases. While the approach is motivated by legal decision making, it also applies to other kinds of decision making, such as commercial decisions about loan applications or employee hiring, as long as the outcome is binary and the input conforms to this paper\u2019s factor- or dimension format. The model is top-level in that it can be extended with more refined accounts of similarities and differences between cases. It is shown to overcome several limitations of similar argumentation-based explanation models, which only have binary features and do not represent the tendency of features towards particular outcomes. The results of the experimental evaluation studies indicate that the model may be feasible in practice, but that further development and experimentation is needed to confirm its usefulness as an explanation model. Main challenges here are selecting from a large number of possible explanations, reducing the number of features in the explanations and adding more meaningful information to them. It also remains to be investigated how suitable our approach is for explaining non-linear models.<\/jats:p>","DOI":"10.3233\/aac-210009","type":"journal-article","created":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T13:57:06Z","timestamp":1619531826000},"page":"159-194","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":19,"title":["A top-level model of case-based argumentation for explanation: Formalisation\u00a0and experiments"],"prefix":"10.1177","volume":"13","author":[{"given":"Henry","family":"Prakken","sequence":"first","affiliation":[{"name":"Department of Information and Computing Sciences, Utrecht University, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rosa","family":"Ratsma","sequence":"additional","affiliation":[{"name":"Department of Information and Computing Sciences, Utrecht University, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2021,4,26]]},"reference":[{"key":"ref001","doi-asserted-by":"publisher","DOI":"10.1109\/iccids.2019.8862140"},{"key":"ref002","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2870052"},{"key":"ref003","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(03)00105-X"},{"key":"ref004","doi-asserted-by":"crossref","unstructured":"V.\u00a0Aleven and K.D.\u00a0Ashley, Doing things with factors, in: Proceedings of the Fifth International Conference on Artificial Intelligence and Law, ACM Press, New York, 1995, pp.\u00a031\u201341.","DOI":"10.1145\/222092.222106"},{"key":"ref005","doi-asserted-by":"crossref","unstructured":"K.D.\u00a0Ashley, Toward a computational theory of arguing with precedents: Accomodating multiple interpretations of cases, in: Proceedings of the Second International Conference on Artificial Intelligence and Law, ACM Press, New York, 1989, pp.\u00a039\u2013102.","DOI":"10.1145\/74014.74028"},{"key":"ref006","unstructured":"K.D.\u00a0Ashley, Modeling Legal Argument: Reasoning with Cases and Hypotheticals, MIT Press, Cambridge, MA, 1990."},{"key":"ref007","doi-asserted-by":"crossref","unstructured":"K.D.\u00a0Ashley, Artificial Intelligence and Legal Analytics. New Tools for Law Practice in the Digital Age, Cambridge University Press, Cambridge, 2017.","DOI":"10.1017\/9781316761380"},{"key":"ref008","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2020.103387"},{"key":"ref009","unstructured":"K.D.\u00a0Atkinson, T.J.M.\u00a0Bench-Capon, H.\u00a0Prakken and A.Z.\u00a0Wyner, Argumentation schemes for reasoning about factors with dimensions, in: Legal Knowledge and Information Systems. JURIX 2013: The Twenty-Sixth Annual Conference, K.D.\u00a0Ashley, ed. IOS Press, Amsterdam, 2013, pp.\u00a039\u201348."},{"key":"ref010","doi-asserted-by":"publisher","DOI":"10.1007\/s10506-017-9201-1"},{"key":"ref011","unstructured":"T.J.M.\u00a0Bench-Capon and K.D.\u00a0Atkinson, Dimensions and values for legal CBR, in: Legal Knowledge and Information Systems. JURIX 2017: The Thirtieth Annual Conference, A.Z.\u00a0Wyner and G.\u00a0Casini, eds, IOS Press, Amsterdam, 2017, pp.\u00a027\u201332."},{"key":"ref012","doi-asserted-by":"publisher","DOI":"10.1145\/2514601.2514604"},{"key":"ref013","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(03)00108-5"},{"key":"ref014","doi-asserted-by":"crossref","unstructured":"D.H.\u00a0Berman and C.D.\u00a0Hafner, Representing teleological structure in case-based legal reasoning: The missing link, in: Proceedings of the Fourth International Conference on Artificial Intelligence and Law, ACM Press, New York, 1993, pp.\u00a050\u201359.","DOI":"10.1145\/158976.158982"},{"key":"ref015","doi-asserted-by":"crossref","unstructured":"R.\u00a0Binns, M.\u00a0Van Kleek, M.\u00a0Veale, U.\u00a0Lyngs, J.\u00a0Zhao and N.\u00a0Shadbolt, \u2018it\u2019s reducing a human being to a percentage\u2019; perceptions of justice in algorithmic systems, in: Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems (CHI 2018), ACM Press, New York, 2018, pp.\u00a0377:1\u2013377:14.","DOI":"10.1145\/3173574.3173951"},{"key":"ref016","doi-asserted-by":"publisher","DOI":"10.1007\/s10506-017-9193-x"},{"key":"ref017","doi-asserted-by":"crossref","unstructured":"S.\u00a0Brueninghaus and K.D.\u00a0Ashley, Generating legal arguments and predictions from case texts, in: Proceedings of the Tenth International Conference on Artificial Intelligence and Law, ACM Press, New York, 2005, pp.\u00a065\u201374.","DOI":"10.1145\/1165485.1165497"},{"key":"ref018","unstructured":"O.\u00a0Cocarascu, K.\u00a0\u010cyras and F.\u00a0Toni, Explanatory predictions with artificial neural networks and argumentation, in: Proceedings of the IJCAI\/ECAI-2018 Workshop on Explainable Artificial Intelligence, 2018, pp.\u00a026\u201332."},{"key":"ref019","unstructured":"O.\u00a0Cocarascu, A.\u00a0Stylianou, K.\u00a0\u010cyras and F.\u00a0Toni, Data-empowered argumentation for dialectically explainable predictions, in: Proceedings of the 24th European Conference on Artificial Intelligence (ECAI 2020), 2020, pp.\u00a02449\u20132456."},{"key":"ref020","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.03.012"},{"key":"ref021","unstructured":"K.\u00a0\u010cyras, K.\u00a0Satoh and F.\u00a0Toni, Explanation for case-based reasoning via abstract argumentation, in: Computational Models of Argument, P.\u00a0Baroni, T.F.\u00a0Gordon, T.\u00a0Scheffler and M.\u00a0Stede, eds, Proceedings of COMMA 2016, IOS Press, Amsterdam, 2016, pp.\u00a0243\u2013254."},{"issue":"2","key":"ref022","first-page":"1301","volume":"5","author":"Das K.","year":"2017","journal-title":"International Journal of Innovative Research in Computer and Communication Engineering"},{"key":"ref023","unstructured":"D.\u00a0Dua and C.\u00a0Graff, UCI Machine Learning Repository, 2019, http:\/\/archive.ics.uci.edu\/ml."},{"key":"ref024","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(94)00041-X"},{"key":"ref025","doi-asserted-by":"crossref","unstructured":"M.\u00a0Grabmair, Predicting trade secret case outcomes using argument schemes and learned quantitative value effect tradeoffs, in: Proceedings of the 16th International Conference on Artificial Intelligence and Law, ACM Press, New York, 2017, pp.\u00a089\u201398.","DOI":"10.1145\/3086512.3086521"},{"key":"ref026","doi-asserted-by":"publisher","DOI":"10.1145\/3236009"},{"key":"ref027","doi-asserted-by":"publisher","DOI":"10.1017\/S1352325211000036"},{"key":"ref028","doi-asserted-by":"publisher","DOI":"10.1007\/s10506-019-09245-0"},{"key":"ref029","doi-asserted-by":"crossref","unstructured":"A.J.\u00a0Hunter\u00a0(ed.), Argument and Computation, 5 (2014), Special issue with Tutorials on Structured Argumentation.","DOI":"10.1080\/19462166.2013.869764"},{"key":"ref030","doi-asserted-by":"crossref","unstructured":"E.M.\u00a0Kenny and M.T.\u00a0Keane, Twin-systems to explain artificial neural networks using case-based reasoning: Comparative tests of feature-weighting methods in ANN-CBR twins for XAI, in: Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI-19), 2019, pp.\u00a02708\u20132715.","DOI":"10.24963\/ijcai.2019\/376"},{"key":"ref031","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.07.007"},{"key":"ref032","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-98197-0_6"},{"key":"ref033","doi-asserted-by":"publisher","DOI":"10.1080\/19462166.2013.869766"},{"key":"ref034","unstructured":"C.\u00a0Molnar, Interpretable Machine Learning, 2019, https:\/\/christophm.github.io\/interpretable-ml-book\/."},{"key":"ref035","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-005-4609-5"},{"key":"ref036","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-46581-2_14"},{"key":"ref037","unstructured":"H.\u00a0Prakken, A top-level model of case-based argumentation for explanation, in: Proceedings of the ECAI 2020 Workshop on Dialogue, Explanation and Argumentation for Human-Agent Interaction (DEXA HAI 2020), 2020."},{"key":"ref038","doi-asserted-by":"publisher","DOI":"10.1007\/s10506-021-09284-6"},{"key":"ref039","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008278309945"},{"key":"ref040","doi-asserted-by":"publisher","DOI":"10.1093\/logcom\/ext010"},{"key":"ref041","unstructured":"R.\u00a0Ratsma, Unboxing the Black Box Using Case-Based Argumentation, Master\u2019s thesis, Artificial Intelligence Programme, Utrecht University, Utrecht, 2020."},{"key":"ref042","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"ref043","doi-asserted-by":"publisher","DOI":"10.1007\/s10506-017-9216-7"},{"key":"ref044","doi-asserted-by":"crossref","unstructured":"E.L.\u00a0Rissland and K.D.\u00a0Ashley, A case-based system for trade secrets law, in: Proceedings of the First International Conference on Artificial Intelligence and Law, ACM Press, New York, 1987, pp.\u00a060\u201366.","DOI":"10.1145\/41735.41743"},{"key":"ref045","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0048-x"},{"key":"ref046","unstructured":"Telco Customer Churn, 2018, https:\/\/www.kaggle.com\/blastchar\/telco-customer-churn, version 1."}],"container-title":["Argument &amp; Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/AAC-210009","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/AAC-210009","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/AAC-210009","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T11:53:20Z","timestamp":1777377200000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.3233\/AAC-210009"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,26]]},"references-count":46,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,6,1]]}},"alternative-id":["10.3233\/AAC-210009"],"URL":"https:\/\/doi.org\/10.3233\/aac-210009","relation":{},"ISSN":["1946-2166","1946-2174"],"issn-type":[{"value":"1946-2166","type":"print"},{"value":"1946-2174","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,26]]}}}