{"id":"https://openalex.org/W2135408252","doi":"https://doi.org/10.1109/iri.2007.4296645","title":"Enhancing Text Analysis via Dimensionality Reduction","display_name":"Enhancing Text Analysis via Dimensionality Reduction","publication_year":2007,"publication_date":"2007-08-01","ids":{"openalex":"https://openalex.org/W2135408252","doi":"https://doi.org/10.1109/iri.2007.4296645","mag":"2135408252"},"language":"en","primary_location":{"id":"doi:10.1109/iri.2007.4296645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iri.2007.4296645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE International Conference on Information Reuse and Integration","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/A5042432116","display_name":"David G. Underhill","orcid":null},"institutions":[{"id":"https://openalex.org/I189158971","display_name":"United States Naval Academy","ror":"https://ror.org/00znex860","country_code":"US","type":"education","lineage":["https://openalex.org/I1330347796","https://openalex.org/I189158971","https://openalex.org/I3130687028"]},{"id":"https://openalex.org/I4399598358","display_name":"United States Navy","ror":"https://ror.org/03cs53d16","country_code":"US","type":"government","lineage":["https://openalex.org/I1330347796","https://openalex.org/I3130687028","https://openalex.org/I4399598358"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David G. Underhill","raw_affiliation_strings":["Department Computer Science, U.S. Naval Academy, Annapolis, MD, USA","U.S. Naval Acad., Annapolis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department Computer Science, U.S. Naval Academy, Annapolis, MD, USA","institution_ids":["https://openalex.org/I189158971"]},{"raw_affiliation_string":"U.S. Naval Acad., Annapolis","institution_ids":["https://openalex.org/I189158971","https://openalex.org/I4399598358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084685300","display_name":"Luke K. McDowell","orcid":null},"institutions":[{"id":"https://openalex.org/I189158971","display_name":"United States Naval Academy","ror":"https://ror.org/00znex860","country_code":"US","type":"education","lineage":["https://openalex.org/I1330347796","https://openalex.org/I189158971","https://openalex.org/I3130687028"]},{"id":"https://openalex.org/I4399598358","display_name":"United States Navy","ror":"https://ror.org/03cs53d16","country_code":"US","type":"government","lineage":["https://openalex.org/I1330347796","https://openalex.org/I3130687028","https://openalex.org/I4399598358"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luke K. McDowell","raw_affiliation_strings":["Department Computer Science, U.S. Naval Academy, Annapolis, MD, USA","U.S. Naval Acad., Annapolis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department Computer Science, U.S. Naval Academy, Annapolis, MD, USA","institution_ids":["https://openalex.org/I189158971"]},{"raw_affiliation_string":"U.S. Naval Acad., Annapolis","institution_ids":["https://openalex.org/I189158971","https://openalex.org/I4399598358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075615856","display_name":"David J. Marchette","orcid":null},"institutions":[{"id":"https://openalex.org/I3130687028","display_name":"United States Department of the Navy","ror":"https://ror.org/03ar0mv07","country_code":"US","type":"government","lineage":["https://openalex.org/I1330347796","https://openalex.org/I3130687028"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David J. Marchette","raw_affiliation_strings":["NSWCDD, Dahlgren, VA, USA","Code Q20, NSWCDD, Dahlgren, VA 22448. (540) 653-1910, david.marchette@navy.mil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NSWCDD, Dahlgren, VA, USA","institution_ids":[]},{"raw_affiliation_string":"Code Q20, NSWCDD, Dahlgren, VA 22448. (540) 653-1910, david.marchette@navy.mil","institution_ids":["https://openalex.org/I3130687028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035037349","display_name":"Jeffrey L. Solka","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeffrey L. Solka","raw_affiliation_strings":["NSWCDD, Dahlgren, VA, USA","Code Q20, NSWCDD, Dahlgren, VA 22448. (540) 653-1910, jeffrey.solka@navy.mil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NSWCDD, Dahlgren, VA, USA","institution_ids":[]},{"raw_affiliation_string":"Code Q20, NSWCDD, Dahlgren, VA 22448. (540) 653-1910, jeffrey.solka@navy.mil","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.15910205,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"348","last_page":"353"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9970999956130981,"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"}},"topics":[{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9970999956130981,"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/T10057","display_name":"Face and Expression Recognition","score":0.9954000115394592,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9919000267982483,"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/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.8098342418670654},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.76108717918396},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5121567249298096},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48201480507850647},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4682667553424835},{"id":"https://openalex.org/keywords/online-analytical-processing","display_name":"Online analytical processing","score":0.44838428497314453},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.44020721316337585},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4151822626590729},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.41064780950546265},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3946043848991394},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37814173102378845},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3265140652656555},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1835745871067047},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1294424831867218}],"concepts":[{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.8098342418670654},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.76108717918396},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5121567249298096},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48201480507850647},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4682667553424835},{"id":"https://openalex.org/C201932085","wikidata":"https://www.wikidata.org/wiki/Q642514","display_name":"Online analytical processing","level":3,"score":0.44838428497314453},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.44020721316337585},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4151822626590729},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41064780950546265},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3946043848991394},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37814173102378845},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3265140652656555},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1835745871067047},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1294424831867218},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iri.2007.4296645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iri.2007.4296645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE International Conference on Information Reuse and Integration","raw_type":"proceedings-article"},{"id":"pmh:ADA479796","is_oa":false,"landing_page_url":"http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA479796","pdf_url":null,"source":{"id":"https://openalex.org/S4406923043","display_name":"Defense Technical Information Center (DTIC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"DTIC","raw_type":"Text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.125.4133","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.125.4133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.usna.edu/~lmcdowel/pubs/UnderhillIRI2007Final.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7599999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W166013858","https://openalex.org/W287609105","https://openalex.org/W1507045023","https://openalex.org/W1550295039","https://openalex.org/W1995945562","https://openalex.org/W2006554089","https://openalex.org/W2011726136","https://openalex.org/W2030951871","https://openalex.org/W2079639311","https://openalex.org/W2089497633","https://openalex.org/W2093402979","https://openalex.org/W2118388177","https://openalex.org/W2137570937","https://openalex.org/W2138153039","https://openalex.org/W2148506018","https://openalex.org/W2148694408","https://openalex.org/W2149551942","https://openalex.org/W2435251607","https://openalex.org/W3005198936","https://openalex.org/W4237947392","https://openalex.org/W4250857377","https://openalex.org/W4300835760","https://openalex.org/W6610518301","https://openalex.org/W6633098901","https://openalex.org/W6682126143","https://openalex.org/W6717827561","https://openalex.org/W6776535907"],"related_works":["https://openalex.org/W1995622179","https://openalex.org/W4391160746","https://openalex.org/W1484111231","https://openalex.org/W1552543208","https://openalex.org/W2074396517","https://openalex.org/W2166963679","https://openalex.org/W2187269125","https://openalex.org/W1641615907","https://openalex.org/W3089231081","https://openalex.org/W2093956241"],"abstract_inverted_index":{"Many":[0],"applications":[1],"require":[2],"analyzing":[3],"vast":[4],"amounts":[5],"of":[6,15,74,81,128,142,166],"textual":[7,87,180],"data,":[8,60,130],"but":[9,61],"the":[10,32,72,79,106,120,126,129,155,167,174,190],"size":[11,127],"and":[12,58],"inherent":[13],"noise":[14],"such":[16,48,96],"data":[17,33,181],"can":[18,145],"make":[19],"processing":[20],"very":[21,147],"challenging.":[22],"One":[23],"approach":[24],"to":[25,29,36,65,153],"these":[26],"issues":[27],"is":[28,172],"mathematically":[30],"reduce":[31],"so":[34],"as":[35,97,109,158],"represent":[37],"each":[38,116],"document":[39],"using":[40,154],"only":[41],"a":[42,110,139,186],"few":[43],"dimensions.":[44],"Techniques":[45],"for":[46,56,113,138],"performing":[47],"\"dimensionality":[49],"reduction":[50],"\"":[51],"(DR)":[52],"have":[53,198],"been":[54],"well-studied":[55],"geometric":[57],"numerical":[59],"more":[62,132,191],"rarely":[63],"applied":[64],"text.":[66],"In":[67,104],"this":[68],"paper,":[69],"we":[70,161],"examine":[71],"impact":[73],"five":[75],"DR":[76,117,144,169,194],"techniques":[77,195],"on":[78,85],"accuracy":[80,107,151],"two":[82],"supervised":[83],"classifiers":[84],"three":[86],"sources.":[88],"This":[89,177],"task":[90],"mirrors":[91],"important":[92],"real":[93],"world":[94],"problems,":[95],"classifying":[98],"Web":[99],"pages":[100],"or":[101],"scientific":[102],"articles.":[103],"addition,":[105],"serves":[108],"proxy":[111],"measure":[112],"how":[114],"well":[115],"technique":[118],"preserves":[119],"inter-document":[121],"relationships":[122],"while":[123],"vastly":[124],"reducing":[125],"facilitating":[131],"sophisticated":[133],"analysis.":[134],"We":[135],"show":[136],"that,":[137],"fixed":[140],"number":[141],"dimensions,":[143],"be":[146],"successful":[148],"at":[149],"improving":[150],"compared":[152],"original":[156],"words":[157],"features.":[159],"Surprisingly,":[160],"also":[162],"find":[163],"that":[164,179],"one":[165],"simplest":[168],"techniques,":[170],"MDS,":[171],"among":[173],"most":[175],"effective.":[176],"suggests":[178],"may":[182],"often":[183],"lie":[184],"upon":[185],"linear":[187],"manifold":[188],"where":[189],"complex":[192],"non-linear":[193],"do":[196],"not":[197],"an":[199],"advantage.":[200]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}