{"id":"https://openalex.org/W2070412788","doi":"https://doi.org/10.1145/312129.312186","title":"Fast and effective text mining using linear-time document clustering","display_name":"Fast and effective text mining using linear-time document clustering","publication_year":1999,"publication_date":"1999-08-01","ids":{"openalex":"https://openalex.org/W2070412788","doi":"https://doi.org/10.1145/312129.312186","mag":"2070412788"},"language":"en","primary_location":{"id":"doi:10.1145/312129.312186","is_oa":true,"landing_page_url":"https://doi.org/10.1145/312129.312186","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/312129.312186","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/312129.312186","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077116939","display_name":"Bjornar Larsen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122838","display_name":"SRA International (United States)","ror":"https://ror.org/02n9cgn70","country_code":"US","type":"company","lineage":["https://openalex.org/I4210122838"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bjornar Larsen","raw_affiliation_strings":["SRA International, Inc., 4300 Fair Lakes Court, Fairfax, VA","SRA International, Inc., 4300 Fair Lakes Court, Fairfax, VA#TAB#"],"affiliations":[{"raw_affiliation_string":"SRA International, Inc., 4300 Fair Lakes Court, Fairfax, VA","institution_ids":["https://openalex.org/I4210122838"]},{"raw_affiliation_string":"SRA International, Inc., 4300 Fair Lakes Court, Fairfax, VA#TAB#","institution_ids":["https://openalex.org/I4210122838"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072841806","display_name":"Chinatsu Aone","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122838","display_name":"SRA International (United States)","ror":"https://ror.org/02n9cgn70","country_code":"US","type":"company","lineage":["https://openalex.org/I4210122838"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chinatsu Aone","raw_affiliation_strings":["SRA International, Inc., 4300 Fair Lakes Court, Fairfax, VA","SRA International, Inc., 4300 Fair Lakes Court, Fairfax, VA#TAB#"],"affiliations":[{"raw_affiliation_string":"SRA International, Inc., 4300 Fair Lakes Court, Fairfax, VA","institution_ids":["https://openalex.org/I4210122838"]},{"raw_affiliation_string":"SRA International, Inc., 4300 Fair Lakes Court, Fairfax, VA#TAB#","institution_ids":["https://openalex.org/I4210122838"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5077116939"],"corresponding_institution_ids":["https://openalex.org/I4210122838"],"apc_list":null,"apc_paid":null,"fwci":23.0577,"has_fulltext":true,"cited_by_count":862,"citation_normalized_percentile":{"value":0.99276236,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"16","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9976000189781189,"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"}},"topics":[{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9976000189781189,"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"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9957000017166138,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9937000274658203,"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/computer-science","display_name":"Computer science","score":0.7394461035728455},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7150302529335022},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.5771872401237488},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4582054615020752},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.45616963505744934},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2600969970226288}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7394461035728455},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7150302529335022},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5771872401237488},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4582054615020752},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45616963505744934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2600969970226288}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/312129.312186","is_oa":true,"landing_page_url":"https://doi.org/10.1145/312129.312186","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/312129.312186","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/312129.312186","is_oa":true,"landing_page_url":"https://doi.org/10.1145/312129.312186","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/312129.312186","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2070412788.pdf","grobid_xml":"https://content.openalex.org/works/W2070412788.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1521439890","https://openalex.org/W1833785989","https://openalex.org/W1981697855","https://openalex.org/W1996764654","https://openalex.org/W1998224037","https://openalex.org/W2008375984","https://openalex.org/W2040058125","https://openalex.org/W2045370125","https://openalex.org/W2074449313","https://openalex.org/W2127218421","https://openalex.org/W2154701989","https://openalex.org/W2156985538","https://openalex.org/W4241122026","https://openalex.org/W6631328736"],"related_works":["https://openalex.org/W2019737068","https://openalex.org/W2899601636","https://openalex.org/W4254379378","https://openalex.org/W3015674157","https://openalex.org/W4206655101","https://openalex.org/W4237592971","https://openalex.org/W1562544158","https://openalex.org/W2387982377","https://openalex.org/W4319309495","https://openalex.org/W2189422997"],"abstract_inverted_index":{"Clustering":[0],"is":[1],"a":[2,24,37,52,62,69,132,138,144,165],"powerful":[3],"technique":[4],"for":[5,57,64],"large-scale":[6],"topic":[7],"discovery":[8],"from":[9,104],"text.":[10],"It":[11,128],"involves":[12],"two":[13],"phases:":[14],"first,":[15],"feature":[16,89,93],"extraction":[17],"maps":[18],"each":[19,58],"document":[20],"or":[21],"record":[22],"to":[23,121,146,164,172],"point":[25],"in":[26,72],"high-dimensional":[27],"space,":[28],"then":[29],"clustering":[30,48,100,170],"algorithms":[31,163],"automatically":[32],"group":[33,166],"the":[34,66,78,99,160,174],"points":[35],"into":[36],"hierarchy":[38,71],"of":[39,54,68,74,80],"clusters.":[40],"We":[41,60,142,157],"describe":[42,143],"an":[43],"unsupervised,":[44],"near-linear":[45,161],"time":[46,162],"text":[47],"system":[49],"that":[50,115,130,152],"offers":[51],"number":[53],"algorithm":[55,136,171],"choices":[56],"phase.":[59],"introduce":[61],"methodology":[63],"measuring":[65],"quality":[67,123],"cluster":[70,122,155],"terms":[73],"F-Measure,":[75],"and":[76,108,110],"present":[77],"results":[79],"experiments":[81,113],"comparing":[82],"different":[83],"algorithms.":[84],"The":[85],"evaluation":[86],"considers":[87],"some":[88],"selection":[90,126,135],"parameters":[91],"(tfidfand":[92],"vector":[94],"length)":[95],"but":[96],"focuses":[97],"on":[98],"algorithms,":[101],"namely":[102],"techniques":[103],"Scatter/Gather":[105],"(buckshot,":[106],"fractionation,":[107],"split/join)":[109],"kmeans.":[111],"Our":[112],"suggest":[114],"continuous":[116],"center":[117,147],"adjustment":[118],"contributes":[119],"more":[120],"than":[124],"seed":[125,134],"does.":[127],"follows":[129],"using":[131],"simpler":[133],"gives":[137],"better":[139],"time/quality":[140,175],"tradeoff.":[141],"refinement":[145],"adjustment,":[148],"\"vector":[149],"average":[150,167],"damping,\"":[151],"further":[153],"improves":[154],"quality.":[156],"also":[158],"compare":[159],"greedy":[168],"agglomerative":[169],"demonstrate":[173],"tradeoff":[176],"quantitatively.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":36},{"year":2019,"cited_by_count":33},{"year":2018,"cited_by_count":32},{"year":2017,"cited_by_count":34},{"year":2016,"cited_by_count":37},{"year":2015,"cited_by_count":39},{"year":2014,"cited_by_count":41},{"year":2013,"cited_by_count":67},{"year":2012,"cited_by_count":53}],"updated_date":"2026-02-25T23:00:34.991745","created_date":"2025-10-10T00:00:00"}