{"id":"https://openalex.org/W2057963304","doi":"https://doi.org/10.1142/s021964920600144x","title":"Efficiency Considerations for Vertical kNN Text Categorisation","display_name":"Efficiency Considerations for Vertical kNN Text Categorisation","publication_year":2006,"publication_date":"2006-09-01","ids":{"openalex":"https://openalex.org/W2057963304","doi":"https://doi.org/10.1142/s021964920600144x","mag":"2057963304"},"language":"en","primary_location":{"id":"doi:10.1142/s021964920600144x","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s021964920600144x","pdf_url":null,"source":{"id":"https://openalex.org/S30163770","display_name":"Journal of Information & Knowledge Management","issn_l":"0219-6492","issn":["0219-6492","1793-6926"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information & Knowledge Management","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/A5088087251","display_name":"Imad Rahal","orcid":"https://orcid.org/0009-0004-3231-0115"},"institutions":[{"id":"https://openalex.org/I142823887","display_name":"St. John's University","ror":"https://ror.org/00bgtad15","country_code":"US","type":"education","lineage":["https://openalex.org/I142823887"]},{"id":"https://openalex.org/I84360360","display_name":"College of Saint Benedict and Saint John's University","ror":"https://ror.org/00watgv28","country_code":"US","type":"education","lineage":["https://openalex.org/I84360360"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Imad Rahal","raw_affiliation_strings":["211, Peter Engel Science Center, Computer Science Department, College of St. Benedict and St. John's University, Collegeville, MN 56321, USA"],"affiliations":[{"raw_affiliation_string":"211, Peter Engel Science Center, Computer Science Department, College of St. Benedict and St. John's University, Collegeville, MN 56321, USA","institution_ids":["https://openalex.org/I84360360","https://openalex.org/I142823887"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006534180","display_name":"Hassan Najadat","orcid":"https://orcid.org/0000-0003-1599-6608"},"institutions":[{"id":"https://openalex.org/I156983542","display_name":"Jordan University of Science and Technology","ror":"https://ror.org/03y8mtb59","country_code":"JO","type":"education","lineage":["https://openalex.org/I156983542"]}],"countries":["JO"],"is_corresponding":false,"raw_author_name":"Hassan Najadat","raw_affiliation_strings":["Computer Information Systems Department, Jordan University of Science and Technology, P.O. Box 3030 Irbid, 22110, Jordan","Computer Information Systems Department, Jordan University of Science and Technology, P.O. Box 3030, Irbid 22110, Jordan"],"affiliations":[{"raw_affiliation_string":"Computer Information Systems Department, Jordan University of Science and Technology, P.O. Box 3030 Irbid, 22110, Jordan","institution_ids":["https://openalex.org/I156983542"]},{"raw_affiliation_string":"Computer Information Systems Department, Jordan University of Science and Technology, P.O. Box 3030, Irbid 22110, Jordan","institution_ids":["https://openalex.org/I156983542"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007656388","display_name":"William Perrizo","orcid":null},"institutions":[{"id":"https://openalex.org/I57328836","display_name":"North Dakota State University","ror":"https://ror.org/05h1bnb22","country_code":"US","type":"education","lineage":["https://openalex.org/I57328836"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Perrizo","raw_affiliation_strings":["IACC 258 A15, Computer Science Department, North Dakota State University, Fargo, ND 58105, USA"],"affiliations":[{"raw_affiliation_string":"IACC 258 A15, Computer Science Department, North Dakota State University, Fargo, ND 58105, USA","institution_ids":["https://openalex.org/I57328836"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088087251"],"corresponding_institution_ids":["https://openalex.org/I142823887","https://openalex.org/I84360360"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10612434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"05","issue":"03","first_page":"211","last_page":"222"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9994999766349792,"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":0.9994999766349792,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9986000061035156,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9937000274658203,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7629144787788391},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6382752656936646},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5276374220848083},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.5140072107315063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4810905158519745},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.42603567242622375},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4220600426197052},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4203990399837494},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39974045753479004},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32473209500312805},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3216293752193451}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7629144787788391},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6382752656936646},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5276374220848083},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.5140072107315063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4810905158519745},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.42603567242622375},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4220600426197052},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4203990399837494},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39974045753479004},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32473209500312805},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3216293752193451},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1142/s021964920600144x","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s021964920600144x","pdf_url":null,"source":{"id":"https://openalex.org/S30163770","display_name":"Journal of Information & Knowledge Management","issn_l":"0219-6492","issn":["0219-6492","1793-6926"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information & Knowledge Management","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:wsi:jikmxx:v:05:y:2006:i:03:n:s021964920600144x","is_oa":false,"landing_page_url":"http://www.worldscientific.com/doi/abs/10.1142/S021964920600144X","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"},{"id":"pmh:oai:RePEc:wsi:jikmxx:v:05:y:2006:i:03:p:211-222","is_oa":false,"landing_page_url":"http://www.worldscinet.com/cgi-bin/details.cgi?type=html&id=pii:S021964920600144X","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":"","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4300000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W812309224","https://openalex.org/W1978394996","https://openalex.org/W2140190241","https://openalex.org/W2165612380","https://openalex.org/W2325227998","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4296209631","https://openalex.org/W2561617217","https://openalex.org/W4294811468","https://openalex.org/W2355801475","https://openalex.org/W106004901","https://openalex.org/W2170062176","https://openalex.org/W4206911031","https://openalex.org/W2316648939","https://openalex.org/W4281664374","https://openalex.org/W2375795576"],"abstract_inverted_index":{"The":[0],"importance":[1],"of":[2,9,12,18,37,50,104,114,118],"text":[3,13,40,43],"mining":[4,27],"stems":[5],"from":[6,140],"the":[7,48,93,115,127,132,137,141],"availability":[8],"huge":[10],"volumes":[11],"databases":[14],"holding":[15],"a":[16,29,66,101,145],"wealth":[17],"valuable":[19],"information":[20],"that":[21,90,122],"needs":[22],"to":[23,54,71,99,136],"be":[24],"mined.":[25],"Text":[26,45],"is":[28,39,47,111,121],"coarse":[30],"area":[31],"encompassing":[32],"many":[33],"finer":[34],"branches":[35],"one":[36],"which":[38],"categorisation":[41,46],"or":[42,76],"classification.":[44],"process":[49],"assigning":[51],"class":[52,77],"labels":[53],"documents":[55],"based":[56],"entirely":[57],"on":[58],"their":[59],"textual":[60],"contents":[61],"where":[62],"we":[63],"are":[64],"given":[65],"document":[67],"d,":[68],"and":[69,96,108],"asked":[70],"find":[72,131],"its":[73],"subject":[74],"matter":[75],"label,":[78],"C":[79],"i":[80],".":[81],"In":[82],"this":[83,119],"paper,":[84],"an":[85],"optimised":[86],"k-Nearest":[87],"Neighbours":[88],"classifier":[89,129],"uses":[91],"discretisation,":[92],"P-tree":[94],"technology,":[95],"dimensionality":[97],"reduction":[98],"achieve":[100],"high":[102],"degree":[103],"accuracy,":[105],"space":[106,143],"utilisation":[107],"time":[109],"efficiency":[110],"proposed.":[112],"One":[113],"fundamental":[116],"contributions":[117],"work":[120],"as":[123],"new":[124,138],"samples":[125],"arrive,":[126],"proposed":[128],"can":[130],"k":[133],"nearest":[134],"neighbours":[135],"sample":[139],"training":[142],"without":[144],"single":[146],"database":[147],"scan.":[148]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}