{"id":"https://openalex.org/W1969775453","doi":"https://doi.org/10.4304/jsw.6.9.1837-1843","title":"An Improved Algorithm of Bayesian Text Categorization","display_name":"An Improved Algorithm of Bayesian Text Categorization","publication_year":2011,"publication_date":"2011-08-01","ids":{"openalex":"https://openalex.org/W1969775453","doi":"https://doi.org/10.4304/jsw.6.9.1837-1843","mag":"1969775453"},"language":"en","primary_location":{"id":"doi:10.4304/jsw.6.9.1837-1843","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jsw.6.9.1837-1843","pdf_url":null,"source":{"id":"https://openalex.org/S114141714","display_name":"Journal of Software","issn_l":"1796-217X","issn":["1796-217X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318660","host_organization_name":"Academy Publisher","host_organization_lineage":["https://openalex.org/P4310318660"],"host_organization_lineage_names":["Academy Publisher"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Software","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/A5051907879","display_name":"Tao Dong","orcid":"https://orcid.org/0000-0002-9561-4085"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014243831","display_name":"Wenqian Shang","orcid":"https://orcid.org/0009-0005-0146-1524"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenqian Shang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020477193","display_name":"Haibin Zhu","orcid":"https://orcid.org/0000-0003-1922-1631"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haibin Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.6079,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.95673429,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"6","issue":"9","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":0.9980999827384949,"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":0.9980999827384949,"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":0.9925000071525574,"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"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9824000000953674,"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":0.8817572593688965},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.6560878157615662},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6009771227836609},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5836110711097717},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5659920573234558},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5606205463409424},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5580214858055115},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.5083555579185486},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4956165552139282},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4918854236602783},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45907163619995117},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45804446935653687},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42900437116622925},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3593217730522156},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.1593897044658661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8817572593688965},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.6560878157615662},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6009771227836609},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5836110711097717},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5659920573234558},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5606205463409424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5580214858055115},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.5083555579185486},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4956165552139282},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4918854236602783},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45907163619995117},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45804446935653687},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42900437116622925},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3593217730522156},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.1593897044658661},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.4304/jsw.6.9.1837-1843","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jsw.6.9.1837-1843","pdf_url":null,"source":{"id":"https://openalex.org/S114141714","display_name":"Journal of Software","issn_l":"1796-217X","issn":["1796-217X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318660","host_organization_name":"Academy Publisher","host_organization_lineage":["https://openalex.org/P4310318660"],"host_organization_lineage_names":["Academy Publisher"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Software","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W35497897","https://openalex.org/W1577943466","https://openalex.org/W1585729986","https://openalex.org/W1594031697","https://openalex.org/W2019864860","https://openalex.org/W2020009543","https://openalex.org/W2021945017","https://openalex.org/W2039576845","https://openalex.org/W2108347737","https://openalex.org/W2118020653","https://openalex.org/W2170806743","https://openalex.org/W2348313353","https://openalex.org/W2349460115","https://openalex.org/W2380923453","https://openalex.org/W2993672723","https://openalex.org/W7019963710"],"related_works":["https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2125109223","https://openalex.org/W2390698788","https://openalex.org/W2383063829","https://openalex.org/W2138922887","https://openalex.org/W2082678934","https://openalex.org/W2035261173","https://openalex.org/W2106892947"],"abstract_inverted_index":{"Text":[0],"categorization":[1,52],"is":[2],"a":[3,10],"fundamental":[4],"methodology":[5],"of":[6,13,16,50,80],"text":[7,51],"mining":[8,18,21],"and":[9,19,41],"hot":[11],"topic":[12],"the":[14,55,68,78,91],"research":[15],"data":[17],"web":[20,35],"in":[22,30,90],"recent":[23],"years.":[24],"It":[25],"plays":[26],"an":[27,47],"important":[28],"role":[29],"building":[31],"traditional":[32],"information":[33,39,93],"retrieval,":[34,40],"indexing":[36],"architecture,":[37],"Web":[38],"so":[42],"on.":[43],"This":[44,85],"paper":[45],"presents":[46],"improved":[48,69],"algorithm":[49,72,86],"that":[53,66],"combines":[54],"feature":[56,74],"weighting":[57],"technique":[58],"with":[59],"Naive":[60,81],"Bayesian":[61,82],"classifier.":[62],"Experimental":[63],"results":[64],"show":[65],"using":[67],"Gini":[70],"index":[71],"to":[73],"weight":[75],"can":[76],"improve":[77],"performance":[79],"classifier":[83],"effectively.":[84],"obtains":[87],"good":[88],"application":[89],"sensitive":[92],"recognition":[94],"system.":[95]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}