{"id":"https://openalex.org/W2039346806","doi":"https://doi.org/10.1145/1183614.1183667","title":"Incremental hierarchical clustering of text documents","display_name":"Incremental hierarchical clustering of text documents","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2039346806","doi":"https://doi.org/10.1145/1183614.1183667","mag":"2039346806"},"language":"en","primary_location":{"id":"doi:10.1145/1183614.1183667","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1183614.1183667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM international conference on Information and knowledge management  - CIKM '06","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/A5021557112","display_name":"Nachiketa Sahoo","orcid":"https://orcid.org/0000-0002-6827-8493"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nachiketa Sahoo","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009879041","display_name":"Jamie Callan","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jamie Callan","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071782159","display_name":"Ramayya Krishnan","orcid":"https://orcid.org/0000-0001-9935-2468"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramayya Krishnan","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080706859","display_name":"George T. Duncan","orcid":"https://orcid.org/0000-0002-4931-5316"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Duncan","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046671743","display_name":"Rema Padman","orcid":"https://orcid.org/0000-0003-4250-4357"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rema Padman","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":18.1335,"has_fulltext":false,"cited_by_count":128,"citation_normalized_percentile":{"value":0.98918281,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"357","last_page":"357"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9984999895095825,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9984999895095825,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9980999827384949,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9980000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7474491000175476},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6015718579292297},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5146923661231995},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.485318124294281},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.46923500299453735},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.4319272041320801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.403422474861145}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7474491000175476},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6015718579292297},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5146923661231995},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.485318124294281},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.46923500299453735},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.4319272041320801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.403422474861145}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/1183614.1183667","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1183614.1183667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM international conference on Information and knowledge management  - CIKM '06","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.404.1044","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.404.1044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ml.cmu.edu/research/dap-papers/sahoo_kdd_project.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.68.8599","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.68.8599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~callan/Papers/cikm06-nsahoo.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.91.4157","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.91.4157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.andrew.cmu.edu/user/nsahoo/incr-hier-clust.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.94.9876","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.94.9876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.andrew.cmu.edu/user/nsahoo/draft6.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W112079613","https://openalex.org/W267247316","https://openalex.org/W1504491975","https://openalex.org/W1506845741","https://openalex.org/W1524704912","https://openalex.org/W1547032355","https://openalex.org/W1574901103","https://openalex.org/W1582937231","https://openalex.org/W1604437383","https://openalex.org/W1604630858","https://openalex.org/W1971318281","https://openalex.org/W1980376361","https://openalex.org/W1992419399","https://openalex.org/W1996764654","https://openalex.org/W1998224037","https://openalex.org/W2005677600","https://openalex.org/W2015245929","https://openalex.org/W2038925774","https://openalex.org/W2047720995","https://openalex.org/W2064988570","https://openalex.org/W2066309116","https://openalex.org/W2073308541","https://openalex.org/W2087962968","https://openalex.org/W2092957858","https://openalex.org/W2100151080","https://openalex.org/W2103333826","https://openalex.org/W2113110240","https://openalex.org/W2130395434","https://openalex.org/W2135909747","https://openalex.org/W2149148023","https://openalex.org/W2150102617","https://openalex.org/W2321470647","https://openalex.org/W2435251607","https://openalex.org/W2988864014","https://openalex.org/W4234536190","https://openalex.org/W4234917632","https://openalex.org/W4239673434","https://openalex.org/W4241122026","https://openalex.org/W4300096532"],"related_works":["https://openalex.org/W1795405792","https://openalex.org/W3200375535","https://openalex.org/W2899601636","https://openalex.org/W4254379378","https://openalex.org/W4206655101","https://openalex.org/W52853789","https://openalex.org/W4237592971","https://openalex.org/W4237492828","https://openalex.org/W2105363053","https://openalex.org/W1562544158"],"abstract_inverted_index":{"A":[0],"version":[1],"of":[2,19,26,94],"cobweb/classit":[3],"is":[4],"proposed":[5],"to":[6,16,21,76],"incrementally":[7],"cluster":[8,12],"text":[9,34,44,97],"documents":[10],"into":[11],"hierarchies.":[13],"The":[14],"modification":[15],"classit":[17],"consists":[18],"changes":[20],"the":[22,27,38,50,56,69,88,92],"underlying":[23],"distributional":[24],"assumption":[25],"original":[28,57,89],"algorithm":[29,52],"that":[30,49],"are":[31,40,74],"suggested":[32],"by":[33],"document":[35,45],"data.":[36],"Both":[37],"algorithms":[39],"evaluated":[41],"using":[42],"standard":[43,96],"datasets.":[46],"We":[47],"show":[48],"modified":[51],"performs":[53,85],"better":[54,86],"than":[55,87],"Classit":[58,90],"when":[59],"presented":[60,78],"with":[61],"Reuters":[62],"newswire":[63],"articles":[64],"in":[65,71,79],"temporal":[66],"order,":[67],"i.e.,":[68],"order":[70],"which":[72],"they":[73],"going":[75],"be":[77],"real":[80],"life":[81],"situation.":[82],"It":[83],"also":[84],"on":[91],"larger":[93],"eleven":[95],"clustering":[98],"datasets":[99],"we":[100],"used.":[101]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":15}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}