{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T04:41:19Z","timestamp":1772858479867,"version":"3.50.1"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,4,13]],"date-time":"2024-04-13T00:00:00Z","timestamp":1712966400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,4,13]],"date-time":"2024-04-13T00:00:00Z","timestamp":1712966400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100007243","name":"Vysok\u00e1 \u0160kola Ekonomick\u00e1 v Praze","doi-asserted-by":"publisher","award":["IGA F4\/22\/2021"],"award-info":[{"award-number":["IGA F4\/22\/2021"]}],"id":[{"id":"10.13039\/501100007243","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Adv Data Anal Classif"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1007\/s11634-024-00592-8","type":"journal-article","created":{"date-parts":[[2024,4,13]],"date-time":"2024-04-13T07:01:59Z","timestamp":1712991719000},"page":"619-648","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Comparison of internal evaluation criteria in hierarchical clustering of categorical data"],"prefix":"10.1007","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7624-8104","authenticated-orcid":false,"given":"Zdenek","family":"Sulc","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaroslav","family":"Hornicek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hana","family":"Rezankova","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jana","family":"Cibulkova","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,4,13]]},"reference":[{"key":"592_CR1","first-page":"199","volume-title":"Information theory and an extension of the maximum likelihood principle","author":"H Akaike","year":"1973","unstructured":"Akaike H (1973) Information theory and an extension of the maximum likelihood principle. Springer New York, New York, pp 199\u2013213"},{"issue":"5","key":"592_CR2","doi-asserted-by":"publisher","first-page":"1523","DOI":"10.1007\/s11222-020-09958-2","volume":"30","author":"SE Akhanli","year":"2020","unstructured":"Akhanli SE, Hennig C (2020) Comparing clusterings and numbers of clusters by aggregation of calibrated clustering validity indexes. Stat Comput 30(5):1523\u20131544. https:\/\/doi.org\/10.1007\/s11222-020-09958-2","journal-title":"Stat Comput"},{"issue":"1","key":"592_CR3","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.patcog.2012.07.021","volume":"46","author":"O Arbelaitz","year":"2013","unstructured":"Arbelaitz O, Gurrutxaga I, Muguerza J, P\u00e9rez JM, Perona I (2013) An extensive comparative study of cluster validity indices. Pattern Recognit 46(1):243\u2013256. https:\/\/doi.org\/10.1016\/j.patcog.2012.07.021","journal-title":"Pattern Recognit"},{"key":"592_CR4","unstructured":"Bacher J, Wenzig K, Vogler M (2004) SPSS TwoStep Cluster \u2013 a First Evaluation. Arbeits- und Diskussionspapiere \/ Universit\u00e4t Erlangen-N\u00fcrnberg, Sozialwissenschaftliches Institut, Lehrstuhl f\u00fcr Soziologie. Universit\u00e4t Erlangen-N\u00fcrnberg, Wirtschafts- und Sozialwissenschaftliche Fakult\u00e4t, Sozialwissenschaftliches Institut Lehrstuhl f\u00fcr Soziologie, N\u00fcrnberg"},{"issue":"6","key":"592_CR5","doi-asserted-by":"publisher","first-page":"1560","DOI":"10.1007\/s10618-014-0387-5","volume":"29","author":"L Bai","year":"2015","unstructured":"Bai L, Liang J (2015) Cluster validity functions for categorical data: a solution-space perspective. Data Min Knowl Disc 29(6):1560\u20131597. https:\/\/doi.org\/10.1007\/s10618-014-0387-5","journal-title":"Data Min Knowl Disc"},{"key":"592_CR6","doi-asserted-by":"publisher","unstructured":"Biem A (2003) A model selection criterion for classification: application to HMM topology optimization. In: Proceedings of the seventh international conference on document analysis and recognition. pp 104\u2013108. https:\/\/doi.org\/10.1109\/ICDAR.2003.1227641","DOI":"10.1109\/ICDAR.2003.1227641"},{"key":"592_CR7","doi-asserted-by":"publisher","first-page":"2344","DOI":"10.1214\/13-EJS844","volume":"7","author":"D Bontemps","year":"2013","unstructured":"Bontemps D, Toussile W (2013) Clustering and variable selection for categorical multivariate data. Electron J Stat 7:2344\u20132371. https:\/\/doi.org\/10.1214\/13-EJS844","journal-title":"Electron J Stat"},{"key":"592_CR8","doi-asserted-by":"publisher","unstructured":"Boriah S, Chandola V, Kumar V (2008) Similarity measures for categorical data: a comparative evaluation. In: Proceedings of the eighth SIAM international conference on data mining. pp 243\u2013254. https:\/\/doi.org\/10.1137\/1.9781611972788.22","DOI":"10.1137\/1.9781611972788.22"},{"issue":"3","key":"592_CR9","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1016\/j.patcog.2006.06.026","volume":"40","author":"M Brun","year":"2007","unstructured":"Brun M, Sima C, Hua J, Lowey J, Carroll B, Suh E, Dougherty ER (2007) Model-based evaluation of clustering validation measures. Pattern Recognit 40(3):807\u2013824. https:\/\/doi.org\/10.1016\/j.patcog.2006.06.026","journal-title":"Pattern Recognit"},{"issue":"1","key":"592_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/03610927408827101","volume":"3","author":"T Cali\u0144ski","year":"1974","unstructured":"Cali\u0144ski T, Harabasz J (1974) A dendrite method for cluster analysis. Commun Stat 3(1):1\u201327. https:\/\/doi.org\/10.1080\/03610927408827101","journal-title":"Commun Stat"},{"issue":"1","key":"592_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10115-008-0159-x","volume":"20","author":"K Chen","year":"2009","unstructured":"Chen K, Liu L (2009) Best K: critical clustering structures in categorical datasets. Knowl Inf Syst 20(1):1\u201333. https:\/\/doi.org\/10.1007\/s10115-008-0159-x","journal-title":"Knowl Inf Syst"},{"key":"592_CR12","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1007\/978-3-319-08010-9_50","volume-title":"Web-age information management","author":"L Chen","year":"2014","unstructured":"Chen L, Guo G (2014) Centroid-based classification of categorical data. Web-age information management. Springer, Berlin, pp 472\u2013475"},{"issue":"1","key":"592_CR13","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s00357-010-9049-5","volume":"27","author":"MMT Chiang","year":"2010","unstructured":"Chiang MMT, Mirkin BG (2010) Intelligent choice of the number of clusters in k-means clustering: an experimental study with different cluster spreads. J Classif 27(1):3\u201340. https:\/\/doi.org\/10.1007\/s00357-010-9049-5","journal-title":"J Classif"},{"issue":"1","key":"592_CR14","first-page":"43","volume":"8","author":"SS Choi","year":"2010","unstructured":"Choi SS, Cha SH, Tappert C (2010) A survey of binary similarity and distance measures. J Syst Cybern Inf 8(1):43\u201348","journal-title":"J Syst Cybern Inf"},{"key":"592_CR15","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1037\/0033-2909.111.2.291","volume":"111","author":"JE Corter","year":"1992","unstructured":"Corter JE, Gluck MA (1992) Explaining basic categories: feature predictability and information. Psychol Bull 111:291\u2013303. https:\/\/doi.org\/10.1037\/0033-2909.111.2.291","journal-title":"Psychol Bull"},{"issue":"1","key":"592_CR16","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/BF02294713","volume":"67","author":"E Dimitriadou","year":"2002","unstructured":"Dimitriadou E, Dolni\u010dar S, Weingessel A (2002) An examination of indexes for determining the number of clusters in binary data sets. Psychometrika 67(1):137\u2013159. https:\/\/doi.org\/10.1007\/BF02294713","journal-title":"Psychometrika"},{"key":"592_CR17","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1007\/978-3-642-22732-5_18","volume-title":"External validation measures for nested clustering of text documents","author":"K Draszawka","year":"2011","unstructured":"Draszawka K, Szyma\u0144ski J (2011) External validation measures for nested clustering of text documents. Springer, Berlin, pp 207\u2013225. https:\/\/doi.org\/10.1007\/978-3-642-22732-5_18"},{"issue":"3","key":"592_CR18","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1080\/01969727308546046","volume":"3","author":"JC Dunn","year":"1973","unstructured":"Dunn JC (1973) A fuzzy relative of the isodata process and its use in detecting compact well-separated clusters. J Cybern 3(3):32\u201357. https:\/\/doi.org\/10.1080\/01969727308546046","journal-title":"J Cybern"},{"issue":"2","key":"592_CR19","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1142\/S1793351X13400059","volume":"7","author":"D Ellerman","year":"2013","unstructured":"Ellerman D (2013) An introduction to logical entropy and its relation to shannon entropy. Int J Semant Comput 7(2):121\u2013145. https:\/\/doi.org\/10.1142\/S1793351X13400059","journal-title":"Int J Semant Comput"},{"key":"592_CR20","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1007\/978-1-4615-0953-0_4","volume-title":"A geometric framework for unsupervised anomaly detection","author":"E Eskin","year":"2002","unstructured":"Eskin E, Arnold A, Prerau M, Portnoy L, Stolfo S (2002) A geometric framework for unsupervised anomaly detection. Springer, Boston, pp 77\u2013101. https:\/\/doi.org\/10.1007\/978-1-4615-0953-0_4"},{"key":"592_CR21","unstructured":"Ester M, Kriegel HP, Sander J, Xu X, et al. (1996) A density-based algorithm for discovering clusters in large spatial databases with noise. In: kdd, vol. 96. pp 226\u2013231"},{"key":"592_CR22","volume-title":"Cluster analysis","author":"BS Everitt","year":"2009","unstructured":"Everitt BS, Landau S, Leese M (2009) Cluster analysis, 4th edn. Wiley Publishing, Hoboken","edition":"4"},{"issue":"4","key":"592_CR23","doi-asserted-by":"publisher","first-page":"882","DOI":"10.2307\/2528080","volume":"22","author":"DW Goodall","year":"1966","unstructured":"Goodall DW (1966) A new similarity index based on probability. Biometrics 22(4):882\u2013907","journal-title":"Biometrics"},{"key":"592_CR24","unstructured":"Hahsler M, Buchta C, Gruen B, Hornik K (2021) arules: mining association rules and frequent itemsets. http:\/\/CRAN.R-project.org\/package=arules. R package version 1.7-6"},{"issue":"2\u20133","key":"592_CR25","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1023\/A:1012801612483","volume":"17","author":"M Halkidi","year":"2001","unstructured":"Halkidi M, Batistakis Y, Vazirgiannis M (2001) On clustering validation techniques. J Intell Inf Syst 17(2\u20133):107\u2013145. https:\/\/doi.org\/10.1023\/A:1012801612483","journal-title":"J Intell Inf Syst"},{"key":"592_CR26","unstructured":"Halkidi M, Vazirgiannis M, Hennig C (2015) Method-independent indices for cluster validation and estimating the number of clusters. https:\/\/api.semanticscholar.org\/CorpusID:125551233"},{"key":"592_CR27","volume-title":"Clustering algorithms","author":"J Hartigan","year":"1975","unstructured":"Hartigan J (1975) Clustering algorithms. Wiley, New York"},{"issue":"1","key":"592_CR28","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1007\/s11634-021-00478-z","volume":"16","author":"C Hennig","year":"2022","unstructured":"Hennig C (2022) An empirical comparison and characterisation of nine popular clustering methods. Adv Data Anal Classif 16(1):201\u2013229. https:\/\/doi.org\/10.1007\/s11634-021-00478-z","journal-title":"Adv Data Anal Classif"},{"key":"592_CR29","series-title":"Chapman & Hall \/ CRC Handbooks of Modern Statistical Methods","doi-asserted-by":"publisher","DOI":"10.1201\/b19706","volume-title":"Handbook of Cluster Analysis","author":"C Hennig","year":"2015","unstructured":"Hennig C, Meila M, Murtagh F, Rocci R (2015) Handbook of Cluster Analysis. Chapman & Hall \/ CRC Handbooks of Modern Statistical Methods. CRC Press, Boca Raton"},{"issue":"1","key":"592_CR30","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/BF01908075","volume":"2","author":"L Hubert","year":"1985","unstructured":"Hubert L, Arabie P (1985) Comparing partitions. J Classif 2(1):193\u2013218. https:\/\/doi.org\/10.1007\/BF01908075","journal-title":"J Classif"},{"issue":"2","key":"592_CR31","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1111\/j.2044-8317.1976.tb00714.x","volume":"29","author":"L Hubert","year":"1976","unstructured":"Hubert L, Schultz J (1976) Quadratic assignment as a general data analysis strategy. Br J Math Stat Psychol 29(2):190\u2013241","journal-title":"Br J Math Stat Psychol"},{"key":"592_CR32","doi-asserted-by":"publisher","unstructured":"Kargar M, Izadkhah H, Isazadeh A (2019) Tarimliq: a new internal metric for software clustering analysis. In: 2019 27th Iranian conference on electrical engineering (ICEE). pp 1879\u20131883. https:\/\/doi.org\/10.1109\/IranianCEE.2019.8786745","DOI":"10.1109\/IranianCEE.2019.8786745"},{"key":"592_CR33","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316801","volume-title":"Finding groups in data: an introduction to cluster analysis","author":"Leonard Kaufman","year":"1990","unstructured":"Kaufman Leonard, Rousseeuw Peter J. (1990) Finding groups in data: an introduction to cluster analysis. Wiley, Hoboken"},{"key":"592_CR34","unstructured":"Lin D (1998) An information-theoretic definition of similarity. In: Proceedings of the 15th international conference on machine learning. Morgan Kaufmann, pp 296\u2013304"},{"issue":"4","key":"592_CR35","doi-asserted-by":"publisher","first-page":"1739","DOI":"10.1016\/j.patcog.2011.10.007","volume":"45","author":"Q Liu","year":"2012","unstructured":"Liu Q, Dong G (2012) Cpcq: contrast pattern based clustering quality index for categorical data. Pattern Recogn 45(4):1739\u20131748. https:\/\/doi.org\/10.1016\/j.patcog.2011.10.007","journal-title":"Pattern Recogn"},{"key":"592_CR36","doi-asserted-by":"publisher","unstructured":"Liu Y, Li Z, Xiong H, Gao X, Wu J (2010) Understanding of Internal Clustering Validation Measures. pp 911\u2013916. https:\/\/doi.org\/10.1109\/ICDM.2010.35","DOI":"10.1109\/ICDM.2010.35"},{"key":"592_CR37","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1007\/BF02294245","volume":"50","author":"GW Miligan","year":"1985","unstructured":"Miligan GW, Cooper MC (1985) An examination of procedures for determining the number of clusters in a data set. Psychometrika 50:159\u2013179","journal-title":"Psychometrika"},{"issue":"1","key":"592_CR38","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/BF02294153","volume":"50","author":"G Milligan","year":"1985","unstructured":"Milligan G (1985) An algorithm for generating artificial test clusters. Psychometrika 50(1):123\u2013127","journal-title":"Psychometrika"},{"key":"592_CR39","unstructured":"OSF: Open science framework (2024). https:\/\/osf.io\/"},{"issue":"2","key":"592_CR40","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1007\/s00357-006-0018-y","volume":"23","author":"W Qiu","year":"2006","unstructured":"Qiu W, Joe H (2006) Generation of random clusters with specified degree of separation. J Classif 23(2):315\u2013334","journal-title":"J Classif"},{"key":"592_CR41","unstructured":"Qiu W, Joe H (2015) clusterGeneration: random cluster generation (with Specified Degree of Separation). http:\/\/CRAN.R-project.org\/package=clusterGeneration. R package version 1.3.4"},{"key":"592_CR42","unstructured":"R Core Team (2021) R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. https:\/\/www.R-project.org\/"},{"issue":"336","key":"592_CR43","doi-asserted-by":"publisher","first-page":"846","DOI":"10.1080\/01621459.1971.10482356","volume":"66","author":"WM Rand","year":"1971","unstructured":"Rand WM (1971) Objective criteria for the evaluation of clustering methods. J Am Stat Assoc 66(336):846\u2013850. https:\/\/doi.org\/10.1080\/01621459.1971.10482356","journal-title":"J Am Stat Assoc"},{"key":"592_CR44","unstructured":"Rend\u00f3n E, Abundez IM, Gutierrez C, Zagal SD, Arizmendi A, Quiroz EM, Arzate HE (2011) A comparison of internal and external cluster validation indexes. In: Proceedings of the 2011 American conference on applied mathematics and the 5th WSEAS international conference on computer engineering and applications. World Scientific and Engineering Academy and Society (WSEAS), Stevens Point, Wisconsin, USA, pp 158\u2013163"},{"key":"592_CR45","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1007\/978-3-642-18029-3_18","volume-title":"Evaluation of categorical data clustering","author":"H \u0158ezankov\u00e1","year":"2011","unstructured":"\u0158ezankov\u00e1 H, L\u00f6ster T, H\u00fasek D (2011) Evaluation of categorical data clustering. Springer Verlag, Berlin, pp 173\u2013182. https:\/\/doi.org\/10.1007\/978-3-642-18029-3_18"},{"key":"592_CR46","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","volume":"20","author":"PJ Rousseeuw","year":"1987","unstructured":"Rousseeuw PJ (1987) Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J Comput Appl Math 20:53\u201365. https:\/\/doi.org\/10.1016\/0377-0427(87)90125-7","journal-title":"J Comput Appl Math"},{"issue":"2","key":"592_CR47","doi-asserted-by":"publisher","first-page":"461","DOI":"10.2307\/2958889","volume":"6","author":"G Schwarz","year":"1978","unstructured":"Schwarz G (1978) Estimating the dimension of a model. Ann Stat 6(2):461\u2013464. https:\/\/doi.org\/10.2307\/2958889","journal-title":"Ann Stat"},{"key":"592_CR48","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","volume":"27","author":"CE Shannon","year":"1948","unstructured":"Shannon CE (1948) A mathematical theory of communication. Bell Syst Tech J 27:379\u2013423","journal-title":"Bell Syst Tech J"},{"key":"592_CR49","first-page":"1409","volume":"28","author":"RR Sokal","year":"1958","unstructured":"Sokal RR, Michener CD (1958) A statistical method for evaluating systematic relationships. Univ Kansas Sci Bull 28:1409\u20131438","journal-title":"Univ Kansas Sci Bull"},{"key":"592_CR50","doi-asserted-by":"publisher","unstructured":"de Souto MC, Coelho AL, Faceli K, Sakata TC, Bonadia V, Costa IG (2012) A comparison of external clustering evaluation indices in the context of imbalanced data sets. In: 2012 Brazilian Symposium on Neural Networks. IEEE, pp 49\u201354. https:\/\/doi.org\/10.1109\/SBRN.2012.25","DOI":"10.1109\/SBRN.2012.25"},{"key":"592_CR51","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1108\/eb026526","volume":"28","author":"K Sp\u00e4rck Jones","year":"1972","unstructured":"Sp\u00e4rck Jones K (1972) A statistical interpretation of term specificity and its application in retrieval. J Doc 28:11\u201321. https:\/\/doi.org\/10.1108\/eb026526","journal-title":"J Doc"},{"key":"592_CR52","unstructured":"SPSS (2001) The SPSS TwoStep Cluster component. SPSS, Inc"},{"issue":"1","key":"592_CR53","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0168","volume":"12","author":"T Strauss","year":"2017","unstructured":"Strauss T, von Maltitz MJ (2017) Generalising Ward\u2019s method for use with Manhattan distances. PLOS ONE 12(1):1\u201321. https:\/\/doi.org\/10.1371\/journal.pone.0168","journal-title":"PLOS ONE"},{"issue":"2","key":"592_CR54","first-page":"1","volume":"15","author":"Z \u0160ulc","year":"2018","unstructured":"\u0160ulc Z, Cibulkov\u00e1 J, Proch\u00e1zka J, \u0158ezankov\u00e1 H (2018) Internal evaluation criteria for categorical data in hierarchical clustering: optimal number of clusters determination. Metodoloski zvezki 15(2):1\u201320","journal-title":"Metodoloski zvezki"},{"issue":"5","key":"592_CR55","doi-asserted-by":"publisher","first-page":"2161","DOI":"10.1007\/s00180-022-01209-4","volume":"37","author":"Z \u0160ulc","year":"2022","unstructured":"\u0160ulc Z, Cibulkov\u00e1 J, \u0158ezankov\u00e1 H (2022) Nomclust 2.0: an R package for hierarchical clustering of objects characterized by nominal variables. Comput Stat 37(5):2161\u20132184. https:\/\/doi.org\/10.1007\/s00180-022-01209-4","journal-title":"Comput Stat"},{"issue":"1","key":"592_CR56","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1007\/s00357-019-09317-5","volume":"36","author":"Z \u0160ulc","year":"2019","unstructured":"\u0160ulc Z, \u0158ezankov\u00e1 H (2019) Comparison of similarity measures for categorical data in hierarchical clustering. J Classif 36(1):58\u201372. https:\/\/doi.org\/10.1007\/s00357-019-09317-5","journal-title":"J Classif"},{"issue":"3","key":"592_CR57","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1198\/106186005X59243","volume":"14","author":"R Tibshirani","year":"2005","unstructured":"Tibshirani R, Walther G (2005) Cluster validation by prediction strength. J Comput Graph Stat 14(3):511\u2013528. https:\/\/doi.org\/10.1198\/106186005X59243","journal-title":"J Comput Graph Stat"},{"key":"592_CR58","doi-asserted-by":"publisher","unstructured":"Tomasini CN. Borges E, Machado K, Emmendorfer L (2017) A study on the relationship between internal and external validity indices applied to partitioning and density-based clustering algorithms. In: Proceedings of the 19th international conference on enterprise information systems \u2013 Volume 1: ICEIS. INSTICC, SciTePress, pp 89\u201398. https:\/\/doi.org\/10.5220\/0006317000890098","DOI":"10.5220\/0006317000890098"},{"key":"592_CR59","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1511","author":"I Van Mechelen","year":"2023","unstructured":"Van Mechelen I, Boulesteix AL, Dangl R, Dean N, Hennig C, Leisch F, Steinley D, Warrens MJ (2023) A white paper on good research practices in benchmarking: the case of cluster analysis. WIREs Data Min Knowl Discov. https:\/\/doi.org\/10.1002\/widm.1511","journal-title":"WIREs Data Min Knowl Discov"},{"issue":"4","key":"592_CR60","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1002\/sam.10080","volume":"3","author":"L Vendramin","year":"2010","unstructured":"Vendramin L, Campello RJGB, Hruschka ER (2010) Relative clustering validity criteria: a comparative overview. Stat Anal Data Min ASA Data Sci J 3(4):209\u2013235. https:\/\/doi.org\/10.1002\/sam.10080","journal-title":"Stat Anal Data Min ASA Data Sci J"},{"key":"592_CR61","doi-asserted-by":"publisher","unstructured":"Xavier JC, Canuto AMP, Almeida ND, Gon\u00e7alves LMG (2013) A comparative analysis of dissimilarity measures for clustering categorical data. In: The 2013 international joint conference on neural networks (IJCNN). IEEE, pp 1\u20138. https:\/\/doi.org\/10.1109\/IJCNN.2013.6707039","DOI":"10.1109\/IJCNN.2013.6707039"},{"key":"592_CR62","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1007\/s10618-005-0361-3","volume":"10","author":"Y Zhao","year":"2005","unstructured":"Zhao Y, Karypis G, Fayyad U (2005) Hierarchical clustering algorithms for document datasets. Data Min Knowl Discov 10:141\u2013168. https:\/\/doi.org\/10.1007\/s10618-005-0361-3","journal-title":"Data Min Knowl Discov"}],"container-title":["Advances in Data Analysis and Classification"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11634-024-00592-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11634-024-00592-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11634-024-00592-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T19:03:16Z","timestamp":1758308596000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11634-024-00592-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,13]]},"references-count":62,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["592"],"URL":"https:\/\/doi.org\/10.1007\/s11634-024-00592-8","relation":{},"ISSN":["1862-5347","1862-5355"],"issn-type":[{"value":"1862-5347","type":"print"},{"value":"1862-5355","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,13]]},"assertion":[{"value":"14 March 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 March 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 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 declare that they have no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}