{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:35:02Z","timestamp":1763202902522,"version":"3.37.3"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,4,4]],"date-time":"2024-04-04T00:00:00Z","timestamp":1712188800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,4,4]],"date-time":"2024-04-04T00:00:00Z","timestamp":1712188800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Hum-Cent Intell Syst"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Bayesian networks are commonly used for learning with uncertainty and incorporating expert knowledge. However, they are hard to interpret, especially when the network structure is complex. Methods used to explain Bayesian networks operate under certain assumptions about what constitutes the best explanation, without actually verifying these assumptions. One such common assumption is that a shorter length of the causal chain of one variable to another enhances its explanatory strength. Counterfactual explanations gained popularity in artificial intelligence over the last years. It is well-known that it is possible to generate counterfactuals from causal Bayesian networks, but there is no indication which of them are useful for explanatory purposes. In this paper, we examine how to apply findings from psychology to search for counterfactuals that are perceived as more useful explanations for the end user. For this purpose, we have conducted a questionnaire to test whether counterfactuals that change an actionable cause are considered more useful than counterfactuals that change a direct cause. The results of the questionnaire indicate that actionable counterfactuals are preferred regardless of being the direct cause or having a longer causal chain.<\/jats:p>","DOI":"10.1007\/s44230-024-00066-2","type":"journal-article","created":{"date-parts":[[2024,4,4]],"date-time":"2024-04-04T16:02:23Z","timestamp":1712246543000},"page":"286-298","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Evaluating the Usefulness of Counterfactual Explanations from Bayesian Networks"],"prefix":"10.1007","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1922-6790","authenticated-orcid":false,"given":"Raphaela","family":"Butz","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arjen","family":"Hommersom","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ren\u00e9e","family":"Schulz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hans","family":"van Ditmarsch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,4,4]]},"reference":[{"key":"66_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/C2009-0-27609-4","author":"J Pearl","year":"1988","unstructured":"Pearl J. Probabilistic reasoning in intelligent systems: networks of plausible inference. Morgan Kaufmann. 1988. https:\/\/doi.org\/10.1016\/C2009-0-27609-4.","journal-title":"Morgan Kaufmann"},{"issue":"2","key":"66_CR2","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1017\/S026988890200019X","volume":"17","author":"C Lacave","year":"2002","unstructured":"Lacave C, D\u00edez FJ. A review of explanation methods for Bayesian networks. Knowl Eng Rev. 2002;17(2):107\u201327. https:\/\/doi.org\/10.1017\/S026988890200019X.","journal-title":"Knowl. Eng. Rev."},{"key":"66_CR3","unstructured":"European Commission. White Paper on Artificial Intelligence: a European approach to excellence and trust. European Union. 2020."},{"key":"66_CR4","unstructured":"European Commission. Proposal for a Regulation laying down harmonised rules on artificial intelligence. European Union. 2021."},{"key":"66_CR5","doi-asserted-by":"publisher","unstructured":"Barredo Arrieta A, D\u00edaz-Rodr\u00edguez N, Del Ser J, Bennetot A, Tabik S, Barbado A, Garcia S, Gil-Lopez S, Molina D, Benjamins R, Chatila R, Herrera F. Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information Fusion. 2020;58: 82\u2013115. https:\/\/doi.org\/10.1016\/j.inffus.2019.12.012","DOI":"10.1016\/j.inffus.2019.12.012"},{"key":"66_CR6","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3063289","author":"S Wachter","year":"2018","unstructured":"Wachter S, Mittelstadt B, Russell C. Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR. 2018. https:\/\/doi.org\/10.2139\/ssrn.3063289.","journal-title":"Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR"},{"key":"66_CR7","doi-asserted-by":"publisher","unstructured":"Byrne RMJ. Counterfactuals in explainable artificial intelligence (XAI): Evidence from human reasoning. In: Proc. of 28th IJCAI, 2019;pp. 6276\u20136282. https:\/\/doi.org\/10.24963\/ijcai.2019\/876","DOI":"10.24963\/ijcai.2019\/876"},{"key":"66_CR8","doi-asserted-by":"publisher","DOI":"10.2307\/2273738","author":"D Lewis","year":"1973","unstructured":"Lewis D. Counterfactuals Blackwell. 1973. https:\/\/doi.org\/10.2307\/2273738.","journal-title":"Counterfactuals. Blackwell"},{"key":"66_CR9","unstructured":"Russell C, Kusner MJ, Loftus J, Silva R. When worlds collide: Integrating different counterfactual assumptions in fairness. In: Advances in Neural Information Processing Systems. 2017;vol. 30."},{"key":"66_CR10","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511803161","author":"J Pearl","year":"2009","unstructured":"Pearl J. Causality Cambridge University Press. 2009. https:\/\/doi.org\/10.1017\/CBO9780511803161.","journal-title":"Causality. Cambridge University Press"},{"key":"66_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2020.101812","author":"E Kyrimi","year":"2020","unstructured":"Kyrimi E, Mossadegh S, Tai N, Marsh W. An incremental explanation of inference in Bayesian networks for increasing model trustworthiness and supporting clinical decision making. Artif Intell Med. 2020. https:\/\/doi.org\/10.1016\/j.artmed.2020.101812.","journal-title":"Artif Intell Med."},{"key":"66_CR12","doi-asserted-by":"publisher","unstructured":"Timmer ST, Meyer J-JC, Prakken H, Renooij S, Verheij B. A two-phase method for extracting explanatory arguments from Bayesian networks. International Journal of Approximate Reasoning. 2017;80:475\u2013494. https:\/\/doi.org\/10.1016\/j.ijar.2016.09.002","DOI":"10.1016\/j.ijar.2016.09.002"},{"key":"66_CR13","doi-asserted-by":"publisher","unstructured":"Butz R, Schulz R, Hommersom A, van Eekelen M. Investigating the understandability of XAI methods for enhanced user experience: When Bayesian network users became detectives. Artificial Intelligence in Medicine 2022;134. https:\/\/doi.org\/10.1016\/j.artmed.2022.102438","DOI":"10.1016\/j.artmed.2022.102438"},{"key":"66_CR14","doi-asserted-by":"crossref","unstructured":"Schwalbe G, Finzel B. A comprehensive taxonomy for explainable artificial intelligence: a systematic survey of surveys on methods and concepts. Data Mining and Knowledge Discovery. 2023.","DOI":"10.1007\/s10618-022-00867-8"},{"key":"66_CR15","unstructured":"McCarthy J. Programs with common sense. In: Proceedings of the Teddington Conference on the Mechanisation of Thought Processes. 1958;pp. 77\u201384."},{"key":"66_CR16","doi-asserted-by":"publisher","unstructured":"Saeed W, Omlin C. Explainable AI (XAI): A systematic meta-survey of current challenges and future opportunities. Knowledge-Based Systems. 2023;263:110273. https:\/\/doi.org\/10.1016\/j.knosys.2023.110273","DOI":"10.1016\/j.knosys.2023.110273"},{"key":"66_CR17","doi-asserted-by":"publisher","unstructured":"Speith T. A review of taxonomies of explainable artificial intelligence (XAI) methods. In: 2022 ACM Conference on Fairness, Accountability, and Transparency. FAccT \u201922, 2022;pp. 2239\u20132250. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3531146.3534639 .","DOI":"10.1145\/3531146.3534639"},{"key":"66_CR18","unstructured":"Timmer S, Meyer J, Prakken H, Renooij S, Verheij B. Inference and attack in Bayesian networks. In: Proc. of 25th BNAIC, 2013;pp. 199\u2013206."},{"key":"66_CR19","doi-asserted-by":"publisher","unstructured":"Vreeswijk GAW. Argumentation in Bayesian belief networks. In: Proc. of ArgMAS, 2005;pp. 111\u2013129. https:\/\/doi.org\/10.1007\/978-3-540-32261-0_8","DOI":"10.1007\/978-3-540-32261-0_8"},{"issue":"1","key":"66_CR20","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/s10849-005-9010-x","volume":"15","author":"M Williams","year":"2006","unstructured":"Williams M, Williamson J. Combining argumentation and Bayesian nets for breast cancer prognosis. JoLLI. 2006;15(1):155\u201378. https:\/\/doi.org\/10.1007\/s10849-005-9010-x.","journal-title":"JoLLI"},{"issue":"3","key":"66_CR21","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1172\/JCI125014","volume":"29","author":"G-E Yap","year":"2008","unstructured":"Yap G-E, Tan A-H, Pang H-H. Explaining inferences in Bayesian networks. Applied Intelligence. 2008;29(3):263\u201378. https:\/\/doi.org\/10.1172\/JCI125014.","journal-title":"Applied Intelligence"},{"issue":"3","key":"66_CR22","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1007\/s10506-016-9183-4","volume":"24","author":"CS Vlek","year":"2016","unstructured":"Vlek CS, Prakken H, Renooij S, Verheij B. A method for explaining Bayesian networks for legal evidence with scenarios. Artificial Intelligence and Law. 2016;24(3):285\u2013324. https:\/\/doi.org\/10.1007\/s10506-016-9183-4.","journal-title":"Artificial Intelligence and Law"},{"key":"66_CR23","unstructured":"Carnap R. Meaning and Necessity. University of Chicago Press. 1947."},{"key":"66_CR24","doi-asserted-by":"publisher","unstructured":"Markman K, Lindberg M, Kray L, Galinsky A. Implications of counterfactual structure for creative generation and analytical problem solving. Personality & Social Psychology Bulletin. 2007;33:312\u201324 https:\/\/doi.org\/10.1177\/0146167206296106","DOI":"10.1177\/0146167206296106"},{"issue":"2","key":"66_CR25","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1177\/1088868308316091","volume":"12","author":"K Epstude","year":"2008","unstructured":"Epstude K, Roese NJ. The functional theory of counterfactual thinking. Personality & Social Psychology. 2008;12(2):168\u201392. https:\/\/doi.org\/10.1177\/1088868308316091.","journal-title":"Personality & Social Psychology"},{"issue":"3","key":"66_CR26","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1002\/ejsp.1858","volume":"42","author":"R Smallman","year":"2012","unstructured":"Smallman R, McCulloch K. Learning from yesterday\u2019s mistakes to fix tomorrow\u2019s problems: when functional counterfactual thinking and psychological distance collide. European Journal of Social Psychology. 2012;42(3):383\u201390. https:\/\/doi.org\/10.1002\/ejsp.1858.","journal-title":"European Journal of Social Psychology"},{"key":"66_CR27","doi-asserted-by":"publisher","unstructured":"Tversky A, Kahneman D. Judgment under uncertainty: Heuristics and biases. In: Utility, Probability, and Human Decision Making. 1975;pp. 141\u2013162. https:\/\/doi.org\/10.1126\/science.185.4157.1124","DOI":"10.1126\/science.185.4157.1124"},{"key":"66_CR28","doi-asserted-by":"publisher","unstructured":"Rim S, Summerville A. How far to the road not taken? The effect of psychological distance on counterfactual direction. Personality & Social Psychology Bulletin. 2013;40. https:\/\/doi.org\/10.1177\/0146167213513304","DOI":"10.1177\/0146167213513304"},{"issue":"3","key":"66_CR29","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1177\/0146167208328329","volume":"35","author":"DR Beike","year":"2009","unstructured":"Beike DR, Markman KD, Karadogan F. What we regret most are lost opportunities: A theory of regret intensity. Personality & Social Psychology Bulletin. 2009;35(3):385\u201397. https:\/\/doi.org\/10.1177\/0146167208328329.","journal-title":"Personality & Social Psychology Bulletin"},{"key":"66_CR30","doi-asserted-by":"publisher","unstructured":"Rips L, Edwards B. Inference and explanation in counterfactual reasoning. Cognitive science 2013;37. https:\/\/doi.org\/10.1111\/cogs.12024","DOI":"10.1111\/cogs.12024"},{"key":"66_CR31","first-page":"163","volume-title":"Case-Based Reasoning Research and Development","author":"MT Keane","year":"2020","unstructured":"Keane MT, Smyth B. Good counterfactuals and where to find them: A case-based technique for generating counterfactuals for explainable AI(XAI). In: Watson I, Weber R, editors. Case-Based Reasoning Research and Development. Cham: Springer; 2020. p. 163\u201378."},{"key":"66_CR32","doi-asserted-by":"publisher","unstructured":"Miller T. Contrastive explanation: a structural-model approach. The Knowledge Engineering Review 2021;36. https:\/\/doi.org\/10.1017\/s0269888921000102","DOI":"10.1017\/s0269888921000102"},{"key":"66_CR33","doi-asserted-by":"publisher","DOI":"10.1201\/b10391","author":"KB Korb","year":"2010","unstructured":"Korb KB, Nicholson AE. Bayesian Artificial Intelligence CRC Press. 2010. https:\/\/doi.org\/10.1201\/b10391.","journal-title":"Bayesian Artificial Intelligence. CRC Press"},{"key":"66_CR34","unstructured":"Peters J, Janzing D, Sch\u00f6lkopf B. Elements of causal inference: foundations and learning algorithms. 2017."},{"key":"66_CR35","doi-asserted-by":"publisher","unstructured":"Balke A, Pearl J. Probabilistic evaluation of counterfactual queries. In: Probabilistic and Causal Inference: The Works of Judea Pearl. 2022;pp. 237\u2013254. https:\/\/doi.org\/10.1145\/3501714","DOI":"10.1145\/3501714"},{"key":"66_CR36","doi-asserted-by":"crossref","unstructured":"Lauritzen SL. Graphical models. 1996;17.","DOI":"10.1093\/oso\/9780198522195.001.0001"},{"issue":"2","key":"66_CR37","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1023\/A:1007421730016","volume":"29","author":"J Binder","year":"1997","unstructured":"Binder J, Koller D, Russell S, Kanazawa K. Adaptive probabilistic networks with hidden variables. Machine Learning. 1997;29(2):213\u201344. https:\/\/doi.org\/10.1023\/A:1007421730016.","journal-title":"Machine Learning"}],"container-title":["Human-Centric Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44230-024-00066-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44230-024-00066-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44230-024-00066-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,5]],"date-time":"2024-06-05T07:31:53Z","timestamp":1717572713000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44230-024-00066-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,4]]},"references-count":37,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,6]]}},"alternative-id":["66"],"URL":"https:\/\/doi.org\/10.1007\/s44230-024-00066-2","relation":{},"ISSN":["2667-1336"],"issn-type":[{"type":"electronic","value":"2667-1336"}],"subject":[],"published":{"date-parts":[[2024,4,4]]},"assertion":[{"value":"18 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 March 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 April 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors did not receive support from any organisation for the submitted work. All authors certify that they have no affiliations with or involvement in any organisation or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript. RB wrote the majority of the manuscript and performed the survey and data analysis. AH contributed to the data analysis. AH, RS and HvD gave feedback and suggestions for the manuscript. All authors contributed to the design of the study and take full responsibility for and have read and approved this final version of this manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Financial interest or Non-financial interest"}},{"value":"There are no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}