{"id":"https://openalex.org/W2114450952","doi":"https://doi.org/10.1002/asi.22623","title":"Document clustering using the <scp>LSI</scp> subspace signature model","display_name":"Document clustering using the <scp>LSI</scp> subspace signature model","publication_year":2013,"publication_date":"2013-02-20","ids":{"openalex":"https://openalex.org/W2114450952","doi":"https://doi.org/10.1002/asi.22623","mag":"2114450952"},"language":"en","primary_location":{"id":"doi:10.1002/asi.22623","is_oa":false,"landing_page_url":"https://doi.org/10.1002/asi.22623","pdf_url":null,"source":{"id":"https://openalex.org/S80113298","display_name":"Journal of the American Society for Information Science and Technology","issn_l":"1532-2882","issn":["1532-2882","1532-2890"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Society for Information Science and Technology","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/A5025678265","display_name":"Wenbin Zhu","orcid":"https://orcid.org/0000-0001-9158-335X"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"W.Z. Zhu","raw_affiliation_strings":["College of Information Science and Technology Drexel University  3141 Chestnut Street Philadelphia PA 19104\u20102875","College of Information Science and Technology, Drexel University, 3141 Chestnut Street, Philadelphia, PA 19104-2875"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Technology Drexel University  3141 Chestnut Street Philadelphia PA 19104\u20102875","institution_ids":["https://openalex.org/I72816309"]},{"raw_affiliation_string":"College of Information Science and Technology, Drexel University, 3141 Chestnut Street, Philadelphia, PA 19104-2875","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014617730","display_name":"Robert B. Allen","orcid":"https://orcid.org/0000-0002-4059-2587"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R.B. Allen","raw_affiliation_strings":["College of Information Science and Technology Drexel University  3141 Chestnut Street Philadelphia PA 19104\u20102875","College of Information Science and Technology, Drexel University, 3141 Chestnut Street, Philadelphia, PA 19104-2875"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Technology Drexel University  3141 Chestnut Street Philadelphia PA 19104\u20102875","institution_ids":["https://openalex.org/I72816309"]},{"raw_affiliation_string":"College of Information Science and Technology, Drexel University, 3141 Chestnut Street, Philadelphia, PA 19104-2875","institution_ids":["https://openalex.org/I72816309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5025678265"],"corresponding_institution_ids":["https://openalex.org/I72816309"],"apc_list":null,"apc_paid":null,"fwci":1.4427,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.86254997,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"64","issue":"4","first_page":"844","last_page":"860"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9983000159263611,"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/T10028","display_name":"Topic Modeling","score":0.9983000159263611,"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":0.998199999332428,"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":0.9962999820709229,"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":0.7097790241241455},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6198924779891968},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5927372574806213},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.5722076296806335},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.48432767391204834},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.46906614303588867},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45898449420928955},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.42640089988708496},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42459651827812195},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42195209860801697},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.4194628596305847},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.4165731966495514},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.4150414764881134},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20941013097763062}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7097790241241455},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6198924779891968},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5927372574806213},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5722076296806335},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.48432767391204834},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.46906614303588867},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45898449420928955},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.42640089988708496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42459651827812195},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42195209860801697},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.4194628596305847},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.4165731966495514},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4150414764881134},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20941013097763062},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1002/asi.22623","is_oa":false,"landing_page_url":"https://doi.org/10.1002/asi.22623","pdf_url":null,"source":{"id":"https://openalex.org/S80113298","display_name":"Journal of the American Society for Information Science and Technology","issn_l":"1532-2882","issn":["1532-2882","1532-2890"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Society for Information Science and Technology","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:bla:jinfst:v:64:y:2013:i:4:p:844-860","is_oa":false,"landing_page_url":"http://hdl.handle.net/10.1002/asi.22623","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":[{"id":"https://openalex.org/F4320306122","display_name":"Institute of Museum and Library Services","ror":"https://ror.org/030prv062"},{"id":"https://openalex.org/F4320320802","display_name":"Victoria University of Wellington","ror":"https://ror.org/0040r6f76"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W201758800","https://openalex.org/W1532325895","https://openalex.org/W1546703457","https://openalex.org/W1558769895","https://openalex.org/W1559715289","https://openalex.org/W1566309885","https://openalex.org/W1575942760","https://openalex.org/W1605433909","https://openalex.org/W1651093245","https://openalex.org/W1880262756","https://openalex.org/W1971784203","https://openalex.org/W1984075651","https://openalex.org/W1984251878","https://openalex.org/W1990517717","https://openalex.org/W1991547393","https://openalex.org/W1996430422","https://openalex.org/W2003458432","https://openalex.org/W2013029404","https://openalex.org/W2024472735","https://openalex.org/W2028342611","https://openalex.org/W2040058125","https://openalex.org/W2040870580","https://openalex.org/W2054833259","https://openalex.org/W2057506443","https://openalex.org/W2059212640","https://openalex.org/W2060100661","https://openalex.org/W2070670538","https://openalex.org/W2073459066","https://openalex.org/W2081980673","https://openalex.org/W2093390569","https://openalex.org/W2101834505","https://openalex.org/W2102437193","https://openalex.org/W2107743791","https://openalex.org/W2131904442","https://openalex.org/W2145036943","https://openalex.org/W2147152072","https://openalex.org/W2165612380","https://openalex.org/W2169658215","https://openalex.org/W2319660501","https://openalex.org/W2338093326","https://openalex.org/W3011290429","https://openalex.org/W3207021134","https://openalex.org/W3207342693","https://openalex.org/W4213009331","https://openalex.org/W4233135949","https://openalex.org/W4237791300","https://openalex.org/W4300402905"],"related_works":["https://openalex.org/W2063335787","https://openalex.org/W1500125366","https://openalex.org/W1557970708","https://openalex.org/W2137763598","https://openalex.org/W1575842006","https://openalex.org/W1996059221","https://openalex.org/W2798105344","https://openalex.org/W2029157577","https://openalex.org/W2214276642","https://openalex.org/W2087145538"],"abstract_inverted_index":{"We":[0],"describe":[1],"the":[2,24,31,39,91,107,112,125,154],"latent":[3,41,57],"semantic":[4,13,58],"indexing":[5,59],"subspace":[6,64],"signature":[7],"model":[8,25,110],"(":[9,60],"LSISSM":[10,44,69,122,151],")":[11,62],"for":[12],"content":[14],"representation":[15],"of":[16,34,78,93,127,143,157],"unstructured":[17],"text.":[18],"Grounded":[19],"on":[20,150],"singular":[21],"value":[22],"decomposition,":[23],"represents":[26],"terms":[27],"and":[28,65,73,80,102,111,141],"documents":[29],"by":[30],"distribution":[32],"signatures":[33,47,50],"their":[35,53],"statistical":[36],"contribution":[37,118],"across":[38],"top\u2010ranking":[40],"concept":[42],"dimensions.":[43],"matches":[45],"term":[46,63],"with":[48,106,132],"document":[49,67],"according":[51],"to":[52],"mapping":[54],"coherence":[55],"between":[56],"LSI":[61,66,114],"subspace.":[68],"does":[70],"feature":[71],"reduction":[72],"finds":[74],"a":[75],"low\u2010rank":[76],"approximation":[77],"scalable":[79],"sparse":[81],"term\u2010document":[82],"matrices.":[83],"Experiments":[84],"demonstrate":[85],"that":[86],"this":[87],"approach":[88],"significantly":[89,152],"improves":[90,124],"performance":[92],"major":[94],"clustering":[95],"algorithms":[96],"such":[97],"as":[98],"standard":[99,128,158],"K":[100,129,159],"\u2010means":[101,130,160],"self\u2010organizing":[103],"maps":[104],"compared":[105,131],"vector":[108],"space":[109],"traditional":[113],"model.":[115],"The":[116],"unique":[117],"ranking":[119],"mechanism":[120],"in":[121],"also":[123],"initialization":[126,147],"random":[133],"seeding":[134],"procedure,":[135],"which":[136],"sometimes":[137],"causes":[138],"low":[139],"efficiency":[140],"effectiveness":[142],"clustering.":[144],"A":[145],"two\u2010stage":[146],"strategy":[148],"based":[149],"reduces":[153],"running":[155],"time":[156],"procedures.":[161]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
