{"id":"https://openalex.org/W2131912994","doi":"https://doi.org/10.1109/icdew.2007.4401066","title":"Document Representation and Dimension Reduction for Text Clustering","display_name":"Document Representation and Dimension Reduction for Text Clustering","publication_year":2007,"publication_date":"2007-04-01","ids":{"openalex":"https://openalex.org/W2131912994","doi":"https://doi.org/10.1109/icdew.2007.4401066","mag":"2131912994"},"language":"en","primary_location":{"id":"doi:10.1109/icdew.2007.4401066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdew.2007.4401066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE 23rd International Conference on Data Engineering Workshop","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/A5025106427","display_name":"Mahdi Shafiei","orcid":null},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Mahdi Shafiei","raw_affiliation_strings":["Faculty of Computer Science, Dalhousie University, Halifax, Canada","Dalhousie University Halifax"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, Dalhousie University, Halifax, Canada","institution_ids":["https://openalex.org/I129902397"]},{"raw_affiliation_string":"Dalhousie University Halifax","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026601452","display_name":"Singer Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Singer Wang","raw_affiliation_strings":["Faculty of Computer Science, Dalhousie University, Halifax, Canada","Dalhousie University Halifax"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, Dalhousie University, Halifax, Canada","institution_ids":["https://openalex.org/I129902397"]},{"raw_affiliation_string":"Dalhousie University Halifax","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090778902","display_name":"Roger Zhang","orcid":"https://orcid.org/0009-0004-7292-8489"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Roger Zhang","raw_affiliation_strings":["Faculty of Computer Science, Dalhousie University, Halifax, Canada","Dalhousie University Halifax"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, Dalhousie University, Halifax, Canada","institution_ids":["https://openalex.org/I129902397"]},{"raw_affiliation_string":"Dalhousie University Halifax","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013989913","display_name":"Evangelos Milios","orcid":"https://orcid.org/0000-0001-5549-4675"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Evangelos Milios","raw_affiliation_strings":["Faculty of Computer Science, Dalhousie University, Halifax, Canada","Dalhousie University Halifax"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, Dalhousie University, Halifax, Canada","institution_ids":["https://openalex.org/I129902397"]},{"raw_affiliation_string":"Dalhousie University Halifax","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101559628","display_name":"Bin Tang","orcid":"https://orcid.org/0000-0001-7700-5975"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Bin Tang","raw_affiliation_strings":["Faculty of Computer Science, Dalhousie University, Halifax, Canada","Dalhousie University Halifax"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, Dalhousie University, Halifax, Canada","institution_ids":["https://openalex.org/I129902397"]},{"raw_affiliation_string":"Dalhousie University Halifax","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068098784","display_name":"Jane E. Tougas","orcid":null},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jane Tougas","raw_affiliation_strings":["Faculty of Computer Science, Dalhousie University, Halifax, Canada","Dalhousie University Halifax"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, Dalhousie University, Halifax, Canada","institution_ids":["https://openalex.org/I129902397"]},{"raw_affiliation_string":"Dalhousie University Halifax","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084076822","display_name":"Raymond J. Spiteri","orcid":"https://orcid.org/0000-0002-3513-6237"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ray Spiteri","raw_affiliation_strings":["Faculty of Computer Science, Dalhousie University, Halifax, Canada","Dalhousie University Halifax"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, Dalhousie University, Halifax, Canada","institution_ids":["https://openalex.org/I129902397"]},{"raw_affiliation_string":"Dalhousie University Halifax","institution_ids":["https://openalex.org/I129902397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5025106427"],"corresponding_institution_ids":["https://openalex.org/I129902397"],"apc_list":null,"apc_paid":null,"fwci":2.4148,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.90414214,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"770","last_page":"779"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9969000220298767,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9969000220298767,"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/T10057","display_name":"Face and Expression Recognition","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9879000186920166,"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/cluster-analysis","display_name":"Cluster analysis","score":0.7522916793823242},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.7491576671600342},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.680937647819519},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.5941932797431946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5920765995979309},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5418331027030945},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5402625799179077},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5270602703094482},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.47647616267204285},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.45156338810920715},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4412168264389038},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3546410799026489},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25281453132629395}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7522916793823242},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.7491576671600342},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.680937647819519},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5941932797431946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5920765995979309},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5418331027030945},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5402625799179077},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5270602703094482},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47647616267204285},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.45156338810920715},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4412168264389038},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3546410799026489},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25281453132629395},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icdew.2007.4401066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdew.2007.4401066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE 23rd International Conference on Data Engineering Workshop","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.418.8425","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.418.8425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ccs.njit.edu/inst/source/10TDMM03.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1488854477","https://openalex.org/W1494273468","https://openalex.org/W1551583811","https://openalex.org/W1571401318","https://openalex.org/W1608320902","https://openalex.org/W1878377492","https://openalex.org/W1978394996","https://openalex.org/W2006533296","https://openalex.org/W2020316999","https://openalex.org/W2058982198","https://openalex.org/W2113540758","https://openalex.org/W2125310307","https://openalex.org/W2129066856","https://openalex.org/W2141224535","https://openalex.org/W2147152072","https://openalex.org/W2180101149","https://openalex.org/W2434205482","https://openalex.org/W2435251607","https://openalex.org/W3139328003","https://openalex.org/W4255387915","https://openalex.org/W6632986775","https://openalex.org/W6634228127","https://openalex.org/W6636268891","https://openalex.org/W6639129879","https://openalex.org/W6676556528","https://openalex.org/W6717827561","https://openalex.org/W6791582515"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","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/W2387982377"],"abstract_inverted_index":{"Increasingly":[0],"large":[1],"text":[2,17,35,50],"damsels":[3],"and":[4,72,78,95,122,134,159,185],"the":[5,46,49,68,114,149,164,183],"high":[6],"dimensionality":[7,175],"associated":[8],"with":[9,39,143],"natural":[10],"language":[11],"create":[12],"a":[13,22,96,171,189],"great":[14],"challenge":[15],"in":[16,27,45,108,186],"mining,":[18],"In":[19],"this":[20],"research,":[21],"systematic":[23],"study":[24],"is":[25,168,179],"conducted.":[26],"which":[28],"three":[29,40,60],"different":[30],"document":[31],"representation":[32,62,151,191],"methods":[33,63,85],"for":[34,163],"are":[36,57,65,106,124],"used,":[37],"together":[38],"Dimension":[41],"Reduction":[42],"Techniques":[43],"(DRT),":[44],"context":[47],"of":[48,110,177],"clustering":[51,111,116,154],"problem.":[52],"Several":[53],"standard":[54],"benchmark":[55],"datasets":[56],"used.":[58],"The":[59,82],"Document":[61,102],"considered":[64],"based":[66,100],"on":[67,101,129],"vector":[69],"space":[70],"model,":[71],"they":[73],"include":[74],"word,":[75],"multi-word":[76],"term,":[77],"character":[79],"N-gram":[80,135,160,165],"representations.":[81],"dimension":[83],"reduction":[84],"are.":[86],"independent":[87],"component":[88],"analysis":[89],"(ICA).":[90],"latent":[91],"semantic":[92],"indexing":[93],"(LSI),":[94],"feature":[97],"selection":[98],"technique":[99],"Frequency":[103],"(DF).":[104],"Results":[105],"compared":[107,142,156],"terms":[109],"performance,":[112],"using":[113],"k-means":[115],"algorithm.":[117],"Experiments":[118,145],"show":[119,147],"that":[120,148,170],"ICA":[121,137],"LSI":[123],"clearly":[125],"belter":[126],"than":[127,195],"DF":[128],"all":[130],"darascls.":[131],"For":[132],"word":[133,150],"representation.":[136,161,197],"generally":[138],"gives":[139,152,192],"better":[140,153,193],"results":[141,155],"LSI.":[144],"also":[146],"to":[157,181],"term":[158],"Finally,":[162],"representation,":[166],"it":[167],"demonstrated":[169],"profile":[172],"length":[173],"(before":[174],"reduction)":[176],"2000":[178],"sufficient":[180],"capture":[182],"information":[184],"most":[187],"cases,":[188],"-4-gram":[190],"performance":[194],"3-gram":[196]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
