{"id":"https://openalex.org/W2089347563","doi":"https://doi.org/10.1145/1581114.1581116","title":"A spectral-based clustering algorithm for categorical data using data summaries","display_name":"A spectral-based clustering algorithm for categorical data using data summaries","publication_year":2009,"publication_date":"2009-06-28","ids":{"openalex":"https://openalex.org/W2089347563","doi":"https://doi.org/10.1145/1581114.1581116","mag":"2089347563"},"language":"en","primary_location":{"id":"doi:10.1145/1581114.1581116","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1581114.1581116","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on Data Mining using Matrices and Tensors","raw_type":"proceedings-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/A5048461467","display_name":"Eman Abdu","orcid":null},"institutions":[{"id":"https://openalex.org/I174216632","display_name":"City University of New York","ror":"https://ror.org/00453a208","country_code":"US","type":"education","lineage":["https://openalex.org/I174216632"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eman Abdu","raw_affiliation_strings":["The City University of New York","THE CITY UNIVERSITY OF NEW YORK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The City University of New York","institution_ids":["https://openalex.org/I174216632"]},{"raw_affiliation_string":"THE CITY UNIVERSITY OF NEW YORK","institution_ids":["https://openalex.org/I174216632"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008880027","display_name":"Douglas E. Salane","orcid":null},"institutions":[{"id":"https://openalex.org/I174216632","display_name":"City University of New York","ror":"https://ror.org/00453a208","country_code":"US","type":"education","lineage":["https://openalex.org/I174216632"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Douglas Salane","raw_affiliation_strings":["The City University of New York","THE CITY UNIVERSITY OF NEW YORK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The City University of New York","institution_ids":["https://openalex.org/I174216632"]},{"raw_affiliation_string":"THE CITY UNIVERSITY OF NEW YORK","institution_ids":["https://openalex.org/I174216632"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I174216632"],"apc_list":null,"apc_paid":null,"fwci":1.8121,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.87632502,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9994999766349792,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.7435917258262634},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.6722772717475891},{"id":"https://openalex.org/keywords/spectral-clustering","display_name":"Spectral clustering","score":0.6659029722213745},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.6443295478820801},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5814168453216553},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5436533689498901},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5418385863304138},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.531240701675415},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.5077822804450989},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.49125975370407104},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.4778054356575012},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.4462592601776123},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.43932589888572693},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39593520760536194},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3581255078315735},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12667220830917358}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7435917258262634},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6722772717475891},{"id":"https://openalex.org/C105611402","wikidata":"https://www.wikidata.org/wiki/Q2976589","display_name":"Spectral clustering","level":3,"score":0.6659029722213745},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.6443295478820801},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5814168453216553},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5436533689498901},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5418385863304138},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.531240701675415},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.5077822804450989},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.49125975370407104},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.4778054356575012},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.4462592601776123},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.43932589888572693},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39593520760536194},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3581255078315735},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12667220830917358}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1581114.1581116","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1581114.1581116","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on Data Mining using Matrices and Tensors","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7819880053","display_name":null,"funder_award_id":"430444","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332707","display_name":"John Jay College of Criminal Justice","ror":"https://ror.org/01p9rc392"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1560541823","https://openalex.org/W2004026774","https://openalex.org/W2004791924","https://openalex.org/W2034331023","https://openalex.org/W2041674806","https://openalex.org/W2057320839","https://openalex.org/W2057712948","https://openalex.org/W2064686951","https://openalex.org/W2066335404","https://openalex.org/W2072773380","https://openalex.org/W2099242680","https://openalex.org/W2102880413","https://openalex.org/W2121947440","https://openalex.org/W2122943553","https://openalex.org/W2131904442","https://openalex.org/W2133576408","https://openalex.org/W2139850885","https://openalex.org/W2147152072","https://openalex.org/W2149230623","https://openalex.org/W2165874743","https://openalex.org/W2798909945","https://openalex.org/W2949364901","https://openalex.org/W2979454998","https://openalex.org/W3099514962","https://openalex.org/W3120740533","https://openalex.org/W4236543541"],"related_works":["https://openalex.org/W2160785859","https://openalex.org/W2188840951","https://openalex.org/W2559422900","https://openalex.org/W4301002638","https://openalex.org/W2590117803","https://openalex.org/W3186815950","https://openalex.org/W2393707058","https://openalex.org/W2202413591","https://openalex.org/W2389934482","https://openalex.org/W2388628913"],"abstract_inverted_index":{"We":[0,55,86],"present":[1],"a":[2,45,53,83,143,198],"novel":[3],"spectral-based":[4,178,225],"algorithm":[5,31,65,90,95,115],"for":[6,96,153,217],"clustering":[7,107,160,179,188,220,249],"categorical":[8,159,248],"data":[9,33,72,80,125,148,174,192,204,239],"that":[10,35,137,252,256,280],"combines":[11],"attribute":[12,38,118,165],"relationship":[13],"and":[14,24,40,77,275],"dimension":[15],"reduction":[16],"techniques":[17],"found":[18],"in":[19,82,109,157,233,278],"Principal":[20],"Component":[21],"Analysis":[22],"(PCA)":[23],"Latent":[25],"Semantic":[26],"Indexing":[27],"(LSI).":[28],"The":[29,64],"new":[30],"uses":[32,67,116],"summaries":[34,73],"consist":[36],"of":[37,47,50,70,123,142,145,147,164,173,229,235,238,269,272],"occurrence":[39],"co-occurrence":[41],"frequencies":[42],"to":[43,57,75,88,170,210,246],"create":[44],"set":[46],"vectors":[48,59],"each":[49],"which":[51],"represents":[52],"cluster.":[54],"refer":[56,87],"these":[58],"as":[60,91],"\"candidate":[61],"cluster":[62,78,212],"representatives.\"":[63],"also":[66],"spectral":[68,106,135],"decomposition":[69],"the":[71,79,89,114,117,124,131,139,162,171,191,203,215,227,236,267,270,282],"matrix":[74,121,128],"project":[76],"objects":[81,193,205],"reduced":[84,199],"space.":[85,200],"SCCADDS":[92,102,150,201,230,253],"(Spectral-based":[93],"Clustering":[94],"CAtegorical":[97],"Data":[98,100],"using":[99],"Summaries).":[101],"differs":[103],"from":[104],"other":[105,186],"algorithms":[108,136,180,250],"several":[110],"key":[111],"respects.":[112],"First,":[113],"categories":[119,166],"similarity":[120,127],"instead":[122],"object":[126],"(as":[129],"is":[130,167,231],"case":[132],"with":[133,259],"most":[134,158],"find":[138],"normalized":[140],"cut":[141],"graph":[144],"nodes":[146],"objects).":[149],"scales":[151],"well":[152],"large":[154,273],"datasets":[155,243],"since":[156],"applications":[161],"number":[163,172,237],"small":[168],"relative":[169],"objects.":[175,240],"Second,":[176],"non-recursive":[177],"typically":[181],"require":[182],"K-means":[183,283],"or":[184],"some":[185],"iterative":[187,219],"method":[189],"after":[190],"have":[194],"been":[195],"projected":[196],"into":[197],"clusters":[202,255],"directly":[206],"by":[207,262],"comparing":[208],"them":[209],"candidate":[211],"representatives":[213],"without":[214],"need":[216],"an":[218],"method.":[221],"Third,":[222],"unlike":[223],"standard":[224],"algorithms,":[226,264],"complexity":[228],"linear":[232],"terms":[234],"Results":[241],"on":[242],"widely":[244],"used":[245],"test":[247],"show":[251],"produces":[254],"are":[257],"consistent":[258],"those":[260],"produced":[261],"existing":[263],"while":[265],"avoiding":[266],"computation":[268],"spectra":[271],"matrices":[274],"problems":[276],"inherent":[277],"methods":[279],"employ":[281],"type":[284],"algorithms.":[285]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}