{"id":"https://openalex.org/W2995749251","doi":"https://doi.org/10.1142/s0219622019300064","title":"Clustering Categorical Data: A Survey","display_name":"Clustering Categorical Data: A Survey","publication_year":2019,"publication_date":"2019-12-10","ids":{"openalex":"https://openalex.org/W2995749251","doi":"https://doi.org/10.1142/s0219622019300064","mag":"2995749251"},"language":"en","primary_location":{"id":"doi:10.1142/s0219622019300064","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219622019300064","pdf_url":null,"source":{"id":"https://openalex.org/S207089700","display_name":"International Journal of Information Technology & Decision Making","issn_l":"0219-6220","issn":["0219-6220","1793-6845"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Information Technology & Decision Making","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036615160","display_name":"Sami Naouali","orcid":"https://orcid.org/0000-0002-0501-5581"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sami Naouali","raw_affiliation_strings":["Virtual Reality and Information Technologies, Military Academy of Fondouk Jedid, Nabeul, Tunisia"],"affiliations":[{"raw_affiliation_string":"Virtual Reality and Information Technologies, Military Academy of Fondouk Jedid, Nabeul, Tunisia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030655844","display_name":"Semeh Ben Salem","orcid":"https://orcid.org/0000-0003-3171-7461"},"institutions":[{"id":"https://openalex.org/I2800887215","display_name":"Tunisia Polytechnic School","ror":"https://ror.org/00dse3307","country_code":"TN","type":"education","lineage":["https://openalex.org/I2800887215"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Semeh Ben Salem","raw_affiliation_strings":["Polytechnic School of Tunisia, La Marsa, Tunis B.P. 743, Rue El Khawarizmi 2078, Tunisia"],"affiliations":[{"raw_affiliation_string":"Polytechnic School of Tunisia, La Marsa, Tunis B.P. 743, Rue El Khawarizmi 2078, Tunisia","institution_ids":["https://openalex.org/I2800887215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030805710","display_name":"Zied Chtourou","orcid":"https://orcid.org/0000-0001-7154-6906"},"institutions":[{"id":"https://openalex.org/I4210119561","display_name":"Digital Research Centre of Sfax","ror":"https://ror.org/02s48dm85","country_code":"TN","type":"facility","lineage":["https://openalex.org/I4210119561"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Zied Chtourou","raw_affiliation_strings":["Digital Research Center of Sfax, B.P. 275, Sakiet Ezzit, Sfax 3021, Tunisia"],"affiliations":[{"raw_affiliation_string":"Digital Research Center of Sfax, B.P. 275, Sakiet Ezzit, Sfax 3021, Tunisia","institution_ids":["https://openalex.org/I4210119561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036615160"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1639,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.81797191,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"19","issue":"01","first_page":"49","last_page":"96"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7941293716430664},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.6922290921211243},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6771745085716248},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6711630821228027},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.6704978942871094},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.5741247534751892},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.564195990562439},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5287831425666809},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.5205122828483582},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4753054082393646},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.4483000934123993},{"id":"https://openalex.org/keywords/consensus-clustering","display_name":"Consensus clustering","score":0.43674567341804504},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.43589168787002563},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2947785258293152}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7941293716430664},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.6922290921211243},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6771745085716248},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6711630821228027},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6704978942871094},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.5741247534751892},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.564195990562439},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5287831425666809},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.5205122828483582},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4753054082393646},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.4483000934123993},{"id":"https://openalex.org/C186767784","wikidata":"https://www.wikidata.org/wiki/Q5162841","display_name":"Consensus clustering","level":5,"score":0.43674567341804504},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.43589168787002563},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2947785258293152}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1142/s0219622019300064","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219622019300064","pdf_url":null,"source":{"id":"https://openalex.org/S207089700","display_name":"International Journal of Information Technology & Decision Making","issn_l":"0219-6220","issn":["0219-6220","1793-6845"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Information Technology & Decision Making","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:wsi:ijitdm:v:19:y:2020:i:01:n:s0219622019300064","is_oa":false,"landing_page_url":"https://www.worldscientific.com/doi/abs/10.1142/S0219622019300064","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":87,"referenced_works":["https://openalex.org/W1893018","https://openalex.org/W52245175","https://openalex.org/W168242428","https://openalex.org/W590132924","https://openalex.org/W1128809682","https://openalex.org/W1150705219","https://openalex.org/W1196375415","https://openalex.org/W1523439439","https://openalex.org/W1535281683","https://openalex.org/W1556833935","https://openalex.org/W1964346230","https://openalex.org/W1974687023","https://openalex.org/W1975930544","https://openalex.org/W1978348710","https://openalex.org/W1982869853","https://openalex.org/W1985059878","https://openalex.org/W1987703131","https://openalex.org/W1999349314","https://openalex.org/W1999400784","https://openalex.org/W1999979626","https://openalex.org/W2004320486","https://openalex.org/W2006291409","https://openalex.org/W2007267444","https://openalex.org/W2007635740","https://openalex.org/W2020287868","https://openalex.org/W2020344074","https://openalex.org/W2022201359","https://openalex.org/W2030068474","https://openalex.org/W2040263621","https://openalex.org/W2041674806","https://openalex.org/W2042294955","https://openalex.org/W2045938006","https://openalex.org/W2051165371","https://openalex.org/W2052760675","https://openalex.org/W2057712948","https://openalex.org/W2057923756","https://openalex.org/W2064686951","https://openalex.org/W2066335404","https://openalex.org/W2066435331","https://openalex.org/W2066644521","https://openalex.org/W2067200401","https://openalex.org/W2075188625","https://openalex.org/W2075292410","https://openalex.org/W2076408892","https://openalex.org/W2078407302","https://openalex.org/W2079680557","https://openalex.org/W2083607096","https://openalex.org/W2086829791","https://openalex.org/W2088722350","https://openalex.org/W2089381274","https://openalex.org/W2100826087","https://openalex.org/W2102726448","https://openalex.org/W2106678396","https://openalex.org/W2107183347","https://openalex.org/W2109574129","https://openalex.org/W2109592225","https://openalex.org/W2116838486","https://openalex.org/W2122545749","https://openalex.org/W2122943553","https://openalex.org/W2123480309","https://openalex.org/W2127971792","https://openalex.org/W2128007922","https://openalex.org/W2130880600","https://openalex.org/W2143451122","https://openalex.org/W2144549472","https://openalex.org/W2145099237","https://openalex.org/W2147544689","https://openalex.org/W2149230623","https://openalex.org/W2150853899","https://openalex.org/W2158908968","https://openalex.org/W2168408108","https://openalex.org/W2171832470","https://openalex.org/W2187537484","https://openalex.org/W2272544077","https://openalex.org/W2273643327","https://openalex.org/W2312649565","https://openalex.org/W2323507959","https://openalex.org/W2342408547","https://openalex.org/W2531336713","https://openalex.org/W2560738241","https://openalex.org/W2736087773","https://openalex.org/W2745507219","https://openalex.org/W2800292911","https://openalex.org/W4211007335","https://openalex.org/W4232213988","https://openalex.org/W4234251954","https://openalex.org/W4383988640"],"related_works":["https://openalex.org/W4241767317","https://openalex.org/W2160785859","https://openalex.org/W3168768270","https://openalex.org/W4200404937","https://openalex.org/W2592952084","https://openalex.org/W1491908038","https://openalex.org/W3192757256","https://openalex.org/W4233099250","https://openalex.org/W3197105638","https://openalex.org/W3040962399"],"abstract_inverted_index":{"Clustering":[0],"is":[1],"a":[2,13,57],"complex":[3],"unsupervised":[4],"method":[5],"used":[6,68],"to":[7,116],"group":[8],"most":[9,119],"similar":[10],"observations":[11],"of":[12,46,110,144],"given":[14],"dataset":[15,58],"within":[16],"the":[17,24,44,49,61,118,142,145],"same":[18],"cluster.":[19],"To":[20],"guarantee":[21],"high":[22,29],"efficiency,":[23],"clustering":[25,35,54,92,104,128],"process":[26],"should":[27],"ensure":[28],"accuracy":[30],"and":[31,48,65,81,102,106,114,135],"low":[32],"complexity.":[33],"Many":[34],"methods":[36,75,97,105,129,139],"were":[37,66,76,94,98],"developed":[38,77],"in":[39,59,69,108],"various":[40],"fields":[41],"depending":[42],"on":[43,141],"type":[45,51],"application":[47],"data":[50,62],"considered.":[52],"Categorical":[53],"considers":[55],"segmenting":[56],"which":[60],"are":[63],"categorical":[64,91],"widely":[67],"many":[70],"real-world":[71],"applications.":[72],"Thus":[73],"several":[74],"including":[78],"hard,":[79],"fuzzy":[80,136],"rough":[82,126],"set-based":[83,127],"methods.":[84,137],"In":[85],"this":[86],"survey,":[87],"more":[88],"than":[89,133],"30":[90],"algorithms":[93],"investigated.":[95],"These":[96],"classified":[99,107],"into":[100],"hierarchical":[101],"partitional":[103],"terms":[109],"their":[111],"accuracy,":[112],"precision":[113],"recall":[115],"identify":[117],"prominent":[120],"ones.":[121],"Experimental":[122],"results":[123],"show":[124],"that":[125],"provided":[130,148],"better":[131],"efficiency":[132],"hard":[134],"Besides,":[138],"based":[140],"initialization":[143],"centroids":[146],"also":[147],"good":[149],"results.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}