{"id":"https://openalex.org/W2146327010","doi":"https://doi.org/10.5539/cis.v1n4p79","title":"Text Document Pre-Processing Using the Bayes Formula for Classification Based on the Vector Space Model","display_name":"Text Document Pre-Processing Using the Bayes Formula for Classification Based on the Vector Space Model","publication_year":2008,"publication_date":"2008-10-18","ids":{"openalex":"https://openalex.org/W2146327010","doi":"https://doi.org/10.5539/cis.v1n4p79","mag":"2146327010"},"language":"en","primary_location":{"id":"doi:10.5539/cis.v1n4p79","is_oa":true,"landing_page_url":"https://doi.org/10.5539/cis.v1n4p79","pdf_url":"https://ccsenet.org/journal/index.php/cis/article/download/1058/1074","source":{"id":"https://openalex.org/S2764452479","display_name":"Computer and Information Science","issn_l":"1913-8989","issn":["1913-8989","1913-8997"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310322531","host_organization_name":"Canadian Center of Science and Education","host_organization_lineage":["https://openalex.org/P4310322531"],"host_organization_lineage_names":["Canadian Center of Science and Education"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer and Information Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ccsenet.org/journal/index.php/cis/article/download/1058/1074","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082908944","display_name":"Dino Isa","orcid":null},"institutions":[{"id":"https://openalex.org/I155043079","display_name":"University of Nottingham Malaysia Campus","ror":"https://ror.org/04mz9mt17","country_code":"MY","type":"education","lineage":["https://openalex.org/I142263535","https://openalex.org/I155043079"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Dino Isa","raw_affiliation_strings":["Faculty of Engineering and Computer Science University of Nottingham, Malaysia Campus","Faculty of Engineering and Computer Science, University of Nottingham, Malaysia Campus"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Computer Science University of Nottingham, Malaysia Campus","institution_ids":["https://openalex.org/I155043079"]},{"raw_affiliation_string":"Faculty of Engineering and Computer Science, University of Nottingham, Malaysia Campus","institution_ids":["https://openalex.org/I155043079"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lee Lam Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I155043079","display_name":"University of Nottingham Malaysia Campus","ror":"https://ror.org/04mz9mt17","country_code":"MY","type":"education","lineage":["https://openalex.org/I142263535","https://openalex.org/I155043079"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Lee Lam Hong","raw_affiliation_strings":["Faculty of Engineering and Computer Science University of Nottingham, Malaysia Campus","Faculty of Engineering and Computer Science, University of Nottingham, Malaysia Campus"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Computer Science University of Nottingham, Malaysia Campus","institution_ids":["https://openalex.org/I155043079"]},{"raw_affiliation_string":"Faculty of Engineering and Computer Science, University of Nottingham, Malaysia Campus","institution_ids":["https://openalex.org/I155043079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090657096","display_name":"Vish Kallimani","orcid":null},"institutions":[{"id":"https://openalex.org/I155043079","display_name":"University of Nottingham Malaysia Campus","ror":"https://ror.org/04mz9mt17","country_code":"MY","type":"education","lineage":["https://openalex.org/I142263535","https://openalex.org/I155043079"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"V. P. Kallimani","raw_affiliation_strings":["Faculty of Engineering and Computer Science University of Nottingham, Malaysia Campus","Faculty of Engineering and Computer Science, University of Nottingham, Malaysia Campus"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Computer Science University of Nottingham, Malaysia Campus","institution_ids":["https://openalex.org/I155043079"]},{"raw_affiliation_string":"Faculty of Engineering and Computer Science, University of Nottingham, Malaysia Campus","institution_ids":["https://openalex.org/I155043079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101798262","display_name":"Raj Rajkumar","orcid":"https://orcid.org/0000-0002-0983-7259"},"institutions":[{"id":"https://openalex.org/I155043079","display_name":"University of Nottingham Malaysia Campus","ror":"https://ror.org/04mz9mt17","country_code":"MY","type":"education","lineage":["https://openalex.org/I142263535","https://openalex.org/I155043079"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"R. Rajkumar","raw_affiliation_strings":["Faculty of Engineering and Computer Science University of Nottingham, Malaysia Campus","Faculty of Engineering and Computer Science, University of Nottingham, Malaysia Campus"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Computer Science University of Nottingham, Malaysia Campus","institution_ids":["https://openalex.org/I155043079"]},{"raw_affiliation_string":"Faculty of Engineering and Computer Science, University of Nottingham, Malaysia Campus","institution_ids":["https://openalex.org/I155043079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I155043079"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.11364082,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"1","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9991999864578247,"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":0.9991999864578247,"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":0.993399977684021,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9871000051498413,"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":0.7753652334213257},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.7327341437339783},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.7076194286346436},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6265944242477417},{"id":"https://openalex.org/keywords/bayes-classifier","display_name":"Bayes classifier","score":0.6044855713844299},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.6022729277610779},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5880447626113892},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.566465437412262},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5278893709182739},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5103313326835632},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.4970701038837433},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4880727529525757},{"id":"https://openalex.org/keywords/bayes-error-rate","display_name":"Bayes error rate","score":0.47507375478744507},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.42531827092170715},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4208301603794098},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.4203537404537201},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3945973217487335},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37783724069595337},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.2431497871875763},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17531585693359375},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13007128238677979}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7753652334213257},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.7327341437339783},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.7076194286346436},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6265944242477417},{"id":"https://openalex.org/C185207860","wikidata":"https://www.wikidata.org/wiki/Q17004744","display_name":"Bayes classifier","level":4,"score":0.6044855713844299},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.6022729277610779},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5880447626113892},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.566465437412262},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5278893709182739},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5103313326835632},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.4970701038837433},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4880727529525757},{"id":"https://openalex.org/C143809311","wikidata":"https://www.wikidata.org/wiki/Q4874458","display_name":"Bayes error rate","level":5,"score":0.47507375478744507},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.42531827092170715},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4208301603794098},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.4203537404537201},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3945973217487335},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37783724069595337},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2431497871875763},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17531585693359375},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13007128238677979},{"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5539/cis.v1n4p79","is_oa":true,"landing_page_url":"https://doi.org/10.5539/cis.v1n4p79","pdf_url":"https://ccsenet.org/journal/index.php/cis/article/download/1058/1074","source":{"id":"https://openalex.org/S2764452479","display_name":"Computer and Information Science","issn_l":"1913-8989","issn":["1913-8989","1913-8997"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310322531","host_organization_name":"Canadian Center of Science and Education","host_organization_lineage":["https://openalex.org/P4310322531"],"host_organization_lineage_names":["Canadian Center of Science and Education"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer and Information Science","raw_type":"journal-article"},{"id":"pmh:oai:eprints.nottingham.ac.uk:2995","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402014","display_name":"Nottingham ePrints (University of Nottingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142263535","host_organization_name":"University of Nottingham","host_organization_lineage":["https://openalex.org/I142263535"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.5539/cis.v1n4p79","is_oa":true,"landing_page_url":"https://doi.org/10.5539/cis.v1n4p79","pdf_url":"https://ccsenet.org/journal/index.php/cis/article/download/1058/1074","source":{"id":"https://openalex.org/S2764452479","display_name":"Computer and Information Science","issn_l":"1913-8989","issn":["1913-8989","1913-8997"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310322531","host_organization_name":"Canadian Center of Science and Education","host_organization_lineage":["https://openalex.org/P4310322531"],"host_organization_lineage_names":["Canadian Center of Science and Education"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer and Information Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2146327010.pdf","grobid_xml":"https://content.openalex.org/works/W2146327010.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W740415","https://openalex.org/W29050389","https://openalex.org/W74400200","https://openalex.org/W175207608","https://openalex.org/W202303397","https://openalex.org/W1481632895","https://openalex.org/W1493182233","https://openalex.org/W1531110464","https://openalex.org/W1544255050","https://openalex.org/W1550206324","https://openalex.org/W1648885110","https://openalex.org/W1726833030","https://openalex.org/W1869391892","https://openalex.org/W1990054914","https://openalex.org/W2029551688","https://openalex.org/W2062529794","https://openalex.org/W2104378844","https://openalex.org/W2124776405","https://openalex.org/W2124993430","https://openalex.org/W2149684865","https://openalex.org/W2156909104","https://openalex.org/W2166781513","https://openalex.org/W2186382132","https://openalex.org/W2285257517","https://openalex.org/W2858429245","https://openalex.org/W4206686222","https://openalex.org/W4285719527","https://openalex.org/W6606214402","https://openalex.org/W6632602330","https://openalex.org/W6633055515","https://openalex.org/W6674760504"],"related_works":["https://openalex.org/W2057359786","https://openalex.org/W1986699031","https://openalex.org/W1969985447","https://openalex.org/W2034570513","https://openalex.org/W2041448365","https://openalex.org/W2006328505","https://openalex.org/W891638917","https://openalex.org/W4285191047","https://openalex.org/W4365601408","https://openalex.org/W2537862391"],"abstract_inverted_index":{"This":[0],"work":[1],"utilizes":[2],"the":[3,19,23,38,57,61,63,69,75,90,99,104,109,117,138],"Bayes":[4,29,119],"formula":[5,30],"to":[6,11,36,44,59,88,107],"vectorize":[7],"a":[8,12,32,45,93],"document":[9,24,39],"according":[10,43],"probability":[13,54,106],"distribution":[14,55],"based":[15,67],"on":[16,68,92,98],"keywords":[17],"reflecting":[18],"probable":[20],"categories":[21],"that":[22,113],"may":[25],"belong":[26],"to.":[27],"The":[28,123],"gives":[31],"range":[33],"of":[34,49,125,140],"probabilities":[35],"which":[37],"can":[40,84,130],"be":[41,86,131],"assigned":[42],"pre":[46],"determined":[47],"set":[48],"topics":[50],"(categories).":[51],"Using":[52],"this":[53],"as":[56,74,112],"vectors":[58],"represent":[60],"document,":[62,110],"text":[64],"classification":[65],"algorithms":[66],"vector":[70],"space":[71],"model,":[72],"such":[73,111],"Support":[76],"Vector":[77],"Machine":[78],"(SVM)":[79],"and":[80],"Self-Organizing":[81],"Map":[82],"(SOM)":[83],"then":[85],"used":[87],"classify":[89,108],"documents":[91],"multi-dimensional":[94],"level,":[95],"thus":[96],"improving":[97],"results":[100],"obtained":[101],"using":[102,133],"only":[103],"highest":[105],"achieved":[114],"by":[115,121],"implementing":[116],"na\u00efve":[118],"classifier":[120],"itself.":[122],"effects":[124],"an":[126],"inadvertent":[127],"dimensionality":[128],"reduction":[129],"overcome":[132],"these":[134,141],"algorithms.":[135],"We":[136],"compare":[137],"performance":[139],"classifiers":[142],"for":[143],"high":[144],"dimensional":[145],"data.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}
