{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,21]],"date-time":"2025-12-21T08:43:13Z","timestamp":1766306593551,"version":"3.48.0"},"reference-count":23,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T00:00:00Z","timestamp":1758758400000},"content-version":"vor","delay-in-days":267,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Procedia Computer Science"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1016\/j.procs.2025.09.410","type":"journal-article","created":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T22:15:25Z","timestamp":1762467325000},"page":"2878-2887","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Evaluating Clustering Quality in Categorical Data: A Comparative Analysis and Novel Metrics"],"prefix":"10.1016","volume":"270","author":[{"given":"Weronika","family":"\u0141azarz","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Agnieszka","family":"Nowak-Brzezi\u0144ska","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"3","key":"10.1016\/j.procs.2025.09.410_bib1","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1023\/A:1009769707641","article-title":"Extensions to the K-means algorithm for clustering large data sets with categorical values","volume":"2","author":"Huang","year":"1998","journal-title":"Data Mining and Knowledge Discovery"},{"issue":"5","key":"10.1016\/j.procs.2025.09.410_bib2","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1016\/S0306-4379(00)00022-3","article-title":"ROCK: A robust clustering algorithm for categorical attributes","volume":"25","author":"Guha","year":"2000","journal-title":"Information Systems"},{"key":"10.1016\/j.procs.2025.09.410_bib3","doi-asserted-by":"crossref","unstructured":"Barbar\u00e1, Daniel, Yi Li, and Julia Couto. (2002) \u201cCOOLCAT: An Entropy-Based Algorithm for Categorical Clustering.\u201d In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 141-146. New York: Association for Computing Machinery.","DOI":"10.1145\/584887.584888"},{"key":"10.1016\/j.procs.2025.09.410_bib4","doi-asserted-by":"crossref","unstructured":"Boriah, Shyam, Vikas Chandola, and Vipin Kumar. (2008) \u201cSimilarity Measures for Categorical Data: A Comparative Evaluation.\u201d In Proceedings of the 2008 SIAM International Conference on Data Mining, 30: 243-254.","DOI":"10.1137\/1.9781611972788.22"},{"key":"10.1016\/j.procs.2025.09.410_bib5","doi-asserted-by":"crossref","unstructured":"Santos, Tiago, and Luis Z\u00e1rate. (2015) \u201cCategorical Data Clustering: What Similarity Measure to Recommend?\u201d Expert Systems with Applications 42 (3): 1247-1260.","DOI":"10.1016\/j.eswa.2014.09.012"},{"key":"10.1016\/j.procs.2025.09.410_bib6","unstructured":"Vinh, Nguyen Xuan, Julien Epps, and James Bailey. (2010) \u201cInformation Theoretic Measures for Clusterings Comparison: Errors and Experimental Results.\u201d Journal of Machine Learning Research 11: 2837-2854."},{"key":"10.1016\/j.procs.2025.09.410_bib7","doi-asserted-by":"crossref","unstructured":"Jia, Hao, Yiu-ming Cheung, and Jianjun Liu. (2016) \u201cA New Distance Metric for Unsupervised Learning of Categorical Data.\u201d IEEE Transactions on Neural Networks and Learning Systems 27 (5): 1065-1079.","DOI":"10.1109\/TNNLS.2015.2436432"},{"issue":"4","key":"10.1016\/j.procs.2025.09.410_bib8","doi-asserted-by":"crossref","first-page":"1739","DOI":"10.1016\/j.patcog.2011.10.007","article-title":"CPCQ: Contrast pattern based clustering quality index for categorical data","volume":"45","author":"Liu","year":"2012","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.procs.2025.09.410_bib9","doi-asserted-by":"crossref","unstructured":"Hamming, Richard W. (1950) \u201cError Detecting and Error Correcting Codes.\u201d The Bell System Technical Journal 29 (2): 147-160.","DOI":"10.1002\/j.1538-7305.1950.tb00463.x"},{"key":"10.1016\/j.procs.2025.09.410_bib10","unstructured":"Jaccard, Paul. (1901) \u201cEtude de la Distribution Florale dans une Portion des Alpes et du Jura.\u201d Bulletin de la Soci\u00e9t\u00e9 Vaudoise des Sciences Naturelles 37: 547-579."},{"key":"10.1016\/j.procs.2025.09.410_bib11","unstructured":"Lin, Dekang. (1998) \u201cAn Information-Theoretic Definition of Similarity.\u201d In Proceedings of the 15th International Conference on Machine Learning (ICML), 296-304. San Francisco: Morgan Kaufmann."},{"key":"10.1016\/j.procs.2025.09.410_bib12","doi-asserted-by":"crossref","unstructured":"Morini, Ivana, and Sergio Zani. (2012) \u201cA New Class of Weighted Similarity Indices Using Polytomous Variables.\u201d Journal of Classification 29 (2): 199-226.","DOI":"10.1007\/s00357-012-9107-2"},{"key":"10.1016\/j.procs.2025.09.410_bib13","doi-asserted-by":"crossref","unstructured":"Yang, Yizhou, Xindong Guan, and Jianjun You. (2002) \u201cCLOPE: A Fast and Effective Clustering Algorithm for Transactional Data.\u201d Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 8 (1): 682-687.","DOI":"10.1145\/775047.775149"},{"key":"10.1016\/j.procs.2025.09.410_bib14","unstructured":"Mushroom [Dataset]. (1981) UCI Machine Learning Repository."},{"key":"10.1016\/j.procs.2025.09.410_bib15","doi-asserted-by":"crossref","unstructured":"Gavva, Sandeep T., S. C. Karthik, and Srujan Punna. (2024) \u201cClustering Categorical Data: Soft Rounding k-Modes.\u201d Information and Computation 296: 105115.","DOI":"10.1016\/j.ic.2023.105115"},{"key":"10.1016\/j.procs.2025.09.410_bib16","doi-asserted-by":"crossref","unstructured":"Gibson, David, Jon Kleinberg, and Prabhakar Raghavan. (2000) \u201cClustering Categorical Data: An Approach Based on Dynamical Systems.\u201d Data Mining and Knowledge Discovery 8 (3-4): 229-254.","DOI":"10.1007\/s007780050005"},{"key":"10.1016\/j.procs.2025.09.410_bib17","doi-asserted-by":"crossref","unstructured":"Andritsos, Periklis, Panayiotis Tsaparas, Ren\\xB4ee J. Miller, and Kenneth C. Sevcik. (2004) \u201cLIMBO: Scalable Clustering of Categorical Data.\u201d In Proceedings of the 9th International Conference on Extending Database Technology (EDBT), 123-146.","DOI":"10.1007\/978-3-540-24741-8_9"},{"key":"10.1016\/j.procs.2025.09.410_bib18","doi-asserted-by":"crossref","unstructured":"Cheung, Yiu-ming, and Hao Jia. (2013) \u201cA Unified Metric for Categorical and Numerical Attributes in Data Clustering.\u201d In Advances in Knowledge Discovery and Data Mining, Lecture Notes in Computer Science, 7819. Berlin: Springer.","DOI":"10.1007\/978-3-642-37456-2_12"},{"key":"10.1016\/j.procs.2025.09.410_bib19","doi-asserted-by":"crossref","unstructured":"Rezankova, Hana, Tomas Loster, and David Husek. (2011) \u201cEvaluation of Categorical Data Clustering.\u201d In Advances in Intelligent Web Mastering - 3, 173-182. Berlin: Springer.","DOI":"10.1007\/978-3-642-18029-3_18"},{"key":"10.1016\/j.procs.2025.09.410_bib20","doi-asserted-by":"crossref","unstructured":"Yang, Xiaokang, Ming Dong, Yanyan Guo, and Jing-Hao Xue. (2021) \u201cMetric Learning for Categorical and Ambiguous Features: An Adversarial Method.\u201d In Computer Vision - ACCV 2020, 222-238. Berlin: Springer.","DOI":"10.1007\/978-3-030-67661-2_14"},{"key":"10.1016\/j.procs.2025.09.410_bib21","doi-asserted-by":"crossref","unstructured":"Calinski, Tadeusz, and Jerzy Harabasz. (1974) \u201cA Dendrite Method for Cluster Analysis.\u201d Communications in Statistics 3 (1): 1-27.","DOI":"10.1080\/03610917408548446"},{"key":"10.1016\/j.procs.2025.09.410_bib22","doi-asserted-by":"crossref","unstructured":"Davies, David L., and Donald W. Bouldin. (1979) \u201cA Cluster Separation Measure.\u201d IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-1 (2): 224-227.","DOI":"10.1109\/TPAMI.1979.4766909"},{"key":"10.1016\/j.procs.2025.09.410_bib23","doi-asserted-by":"crossref","unstructured":"Dunn, Joseph C. (1974) \u201cWell-Separated Clusters and Optimal Fuzzy Partitions.\u201d Journal of Cybernetics 4 (1): 95-104.","DOI":"10.1080\/01969727408546059"}],"container-title":["Procedia Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1877050925030832?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1877050925030832?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,12,21]],"date-time":"2025-12-21T08:38:20Z","timestamp":1766306300000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1877050925030832"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":23,"alternative-id":["S1877050925030832"],"URL":"https:\/\/doi.org\/10.1016\/j.procs.2025.09.410","relation":{},"ISSN":["1877-0509"],"issn-type":[{"type":"print","value":"1877-0509"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Evaluating Clustering Quality in Categorical Data: A Comparative Analysis and Novel Metrics","name":"articletitle","label":"Article Title"},{"value":"Procedia Computer Science","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.procs.2025.09.410","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}]}}