{"id":"https://openalex.org/W95524657","doi":null,"title":"Recent Developments in Document Clustering","display_name":"Recent Developments in Document Clustering","publication_year":2007,"publication_date":"2007-10-01","ids":{"openalex":"https://openalex.org/W95524657","mag":"95524657"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.104.128","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.104.128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://eprints.cs.vt.edu/archive/00001000/01/docclust.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5111560316","display_name":"Nicholas Andrews","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholas Andrews","raw_affiliation_strings":["Virginia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049148461","display_name":"Edward A. Fox","orcid":"https://orcid.org/0000-0003-1447-6870","observed_orcids":["https://orcid.org/0000-0003-1447-6870"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Edward A. Fox","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1447-6870","affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.0247,"has_fulltext":false,"cited_by_count":169,"citation_normalized_percentile":{"value":0.98170557,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9990000128746033,"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":0.9990000128746033,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.0003000000142492354,"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/T10028","display_name":"Topic Modeling","score":9.999999747378752e-05,"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/document-clustering","display_name":"document clustering","score":0.9959999918937683},{"id":"https://openalex.org/keywords/clustering-algorithms","display_name":"clustering algorithms","score":0.8989999890327454},{"id":"https://openalex.org/keywords/algorithmic-efficiency","display_name":"algorithm efficiency","score":0.8420000076293945},{"id":"https://openalex.org/keywords/clustering-accuracy","display_name":"clustering accuracy","score":0.921999990940094},{"id":"https://openalex.org/keywords/algorithm-comparison","display_name":"algorithm comparison","score":0.6309999823570251}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8670449256896973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6774771213531494},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.550859808921814},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.44849374890327454},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.4169410765171051},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.39389288425445557},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3802160918712616},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2852267026901245}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.104.128","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.104.128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://eprints.cs.vt.edu/archive/00001000/01/docclust.pdf","raw_type":"text"},{"id":"pmh:oai:vtcstechreports.OAI2:1000","doi":null,"is_oa":false,"landing_page_url":"http://eprints.cs.vt.edu/archive/00001000/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400253","display_name":"Computer Science Technical Reports (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"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":"Departmental Technical Report"},{"id":"pmh:oai:vtechworks.lib.vt.edu:10919/19473","doi":null,"is_oa":false,"landing_page_url":"http://eprints.cs.vt.edu/archive/00001000/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"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":"Technical report"},{"id":"mag:95524657","doi":null,"is_oa":false,"landing_page_url":"http://eprints.cs.vt.edu/archive/00001000/01/docclust.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W130742730","https://openalex.org/W575347202","https://openalex.org/W1237351826","https://openalex.org/W1486632395","https://openalex.org/W1500092210","https://openalex.org/W1516414061","https://openalex.org/W1533168581","https://openalex.org/W1534784399","https://openalex.org/W1544355022","https://openalex.org/W1575173685","https://openalex.org/W1600496295","https://openalex.org/W1651093245","https://openalex.org/W1675272512","https://openalex.org/W1790954942","https://openalex.org/W1902027874","https://openalex.org/W1941537533","https://openalex.org/W1971285215","https://openalex.org/W1972619959","https://openalex.org/W1981081578","https://openalex.org/W1986007546","https://openalex.org/W1996764654","https://openalex.org/W2002519017","https://openalex.org/W2013029404","https://openalex.org/W2017732166","https://openalex.org/W2024575163","https://openalex.org/W2026450968","https://openalex.org/W2034331023","https://openalex.org/W2054274648","https://openalex.org/W2064742743","https://openalex.org/W2066680326","https://openalex.org/W2081580037","https://openalex.org/W2093771778","https://openalex.org/W2097645701","https://openalex.org/W2098162425","https://openalex.org/W2098418076","https://openalex.org/W2099242680","https://openalex.org/W2100958137","https://openalex.org/W2117853077","https://openalex.org/W2124089375","https://openalex.org/W2127391575","https://openalex.org/W2129250947","https://openalex.org/W2129932701","https://openalex.org/W2131074607","https://openalex.org/W2133576408","https://openalex.org/W2134737843","https://openalex.org/W2135674549","https://openalex.org/W2137763598","https://openalex.org/W2137843911","https://openalex.org/W2145001205","https://openalex.org/W2155455993","https://openalex.org/W2164755290","https://openalex.org/W2165612380","https://openalex.org/W2168466186","https://openalex.org/W2170478283","https://openalex.org/W2567948266","https://openalex.org/W2885310545"],"related_works":["https://openalex.org/W7097897988","https://openalex.org/W2319531616","https://openalex.org/W4402773186","https://openalex.org/W4390962210","https://openalex.org/W2167971078","https://openalex.org/W2993706643","https://openalex.org/W4398204530","https://openalex.org/W2799277860","https://openalex.org/W7217655054","https://openalex.org/W3085502125"],"abstract_inverted_index":{"This":[0],"report":[1],"aims":[2],"to":[3],"give":[4],"a":[5,21,59],"brief":[6],"overview":[7],"of":[8,12,52],"the":[9,53],"current":[10],"state":[11],"document":[13],"clustering":[14,36,43],"research":[15,73],"and":[16,41,64],"present":[17],"recent":[18],"developments":[19],"in":[20,32],"well-organized":[22],"manner.":[23],"Clustering":[24],"algorithms":[25,54],"are":[26,74],"considered":[27],"with":[28,37,44,58],"two":[29],"hypothetical":[30],"scenarios":[31],"mind:":[33],"online":[34],"query":[35],"tight":[38],"efficiency":[39],"constraints,":[40],"offline":[42],"an":[45],"emphasis":[46],"on":[47],"accuracy.":[48],"A":[49],"comparative":[50],"analysis":[51],"is":[55],"performed":[56],"along":[57],"table":[60],"summarizing":[61],"important":[62],"properties,":[63],"open":[65],"problems":[66],"as":[67,69],"well":[68],"directions":[70],"for":[71],"future":[72],"discussed.":[75]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":16},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":23},{"year":2012,"cited_by_count":14}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2016-06-24T00:00:00"}