{"id":"https://openalex.org/W2920240348","doi":"https://doi.org/10.1145/3297156.3297256","title":"Naive Bayes Text Categorization Algorithm Based on TF-IDF Attribute Weighting","display_name":"Naive Bayes Text Categorization Algorithm Based on TF-IDF Attribute Weighting","publication_year":2018,"publication_date":"2018-12-08","ids":{"openalex":"https://openalex.org/W2920240348","doi":"https://doi.org/10.1145/3297156.3297256","mag":"2920240348"},"language":"en","primary_location":{"id":"doi:10.1145/3297156.3297256","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3297156.3297256","pdf_url":null,"source":{"id":"https://openalex.org/S4306523626","display_name":"Proceedings of the 2018 2nd International Conference on Computer Science and Artificial Intelligence","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 2nd International Conference on Computer Science and Artificial Intelligence","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/A5038024192","display_name":"Feng Jiang","orcid":"https://orcid.org/0000-0001-7369-9498"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Feng Jiang","raw_affiliation_strings":["Jilin University, Jilin University, Chaoyang District, Changchun City, Jilin Province, China"],"affiliations":[{"raw_affiliation_string":"Jilin University, Jilin University, Chaoyang District, Changchun City, Jilin Province, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100714827","display_name":"Zhenghao Zhang","orcid":"https://orcid.org/0000-0002-9056-7750"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenghao Zhang","raw_affiliation_strings":["Jilin University, Jilin University, Chaoyang District, Changchun City, Jilin Province, China"],"affiliations":[{"raw_affiliation_string":"Jilin University, Jilin University, Chaoyang District, Changchun City, Jilin Province, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073787687","display_name":"Ping Chen","orcid":"https://orcid.org/0000-0003-1868-0326"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Chen","raw_affiliation_strings":["Jilin University, Jilin University, Chaoyang District, Changchun City, Jilin Province, China"],"affiliations":[{"raw_affiliation_string":"Jilin University, Jilin University, Chaoyang District, Changchun City, Jilin Province, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061736536","display_name":"Yongrui Liu","orcid":"https://orcid.org/0009-0003-9301-7978"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongrui Liu","raw_affiliation_strings":["Jilin University, Jilin University, Chaoyang District, Changchun City, Jilin Province, China"],"affiliations":[{"raw_affiliation_string":"Jilin University, Jilin University, Chaoyang District, Changchun City, Jilin Province, China","institution_ids":["https://openalex.org/I194450716"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5038024192"],"corresponding_institution_ids":["https://openalex.org/I194450716"],"apc_list":null,"apc_paid":null,"fwci":0.077,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.47996795,"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":"521","last_page":"525"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.991599977016449,"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":0.991599977016449,"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.9700000286102295,"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/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.8376342058181763},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.8025322556495667},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.731777012348175},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6999158263206482},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6234238743782043},{"id":"https://openalex.org/keywords/tf\u2013idf","display_name":"tf\u2013idf","score":0.5436049103736877},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5340614914894104},{"id":"https://openalex.org/keywords/statistic","display_name":"Statistic","score":0.497419148683548},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.47467541694641113},{"id":"https://openalex.org/keywords/statistical-classification","display_name":"Statistical classification","score":0.4437046945095062},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4397830665111542},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4310307502746582},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4298967719078064},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4111863672733307},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35848158597946167},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3313749432563782},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2517470717430115},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.11250916123390198},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10517755150794983},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.10035431385040283},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.06738519668579102}],"concepts":[{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.8376342058181763},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.8025322556495667},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.731777012348175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6999158263206482},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6234238743782043},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.5436049103736877},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5340614914894104},{"id":"https://openalex.org/C89128539","wikidata":"https://www.wikidata.org/wiki/Q1949963","display_name":"Statistic","level":2,"score":0.497419148683548},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.47467541694641113},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.4437046945095062},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4397830665111542},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4310307502746582},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4298967719078064},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4111863672733307},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35848158597946167},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3313749432563782},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2517470717430115},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.11250916123390198},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10517755150794983},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.10035431385040283},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.06738519668579102},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3297156.3297256","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3297156.3297256","pdf_url":null,"source":{"id":"https://openalex.org/S4306523626","display_name":"Proceedings of the 2018 2nd International Conference on Computer Science and Artificial Intelligence","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 2nd International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1972450020","https://openalex.org/W2014283007","https://openalex.org/W2022855932","https://openalex.org/W2045853577","https://openalex.org/W2079737479","https://openalex.org/W2115477592","https://openalex.org/W2157610863","https://openalex.org/W2203023521"],"related_works":["https://openalex.org/W2372663604","https://openalex.org/W2537862391","https://openalex.org/W2417174640","https://openalex.org/W2324052717","https://openalex.org/W2349460115","https://openalex.org/W2897949376","https://openalex.org/W1541869740","https://openalex.org/W2168953691","https://openalex.org/W2363252165","https://openalex.org/W4200385031"],"abstract_inverted_index":{"As":[0],"is":[1,8,63,105],"known":[2],"to":[3,27,35,40,73,87,94],"us,":[4],"Naive":[5,46,53,101],"Bayes":[6,47,54,102],"algorithm":[7,23,48,57,79,124],"a":[9,52],"simple":[10],"and":[11,81,117],"efficient":[12],"categorization":[13,33,43,56,109,130],"algorithm.":[14],"However,":[15],"the":[16,42,70,78,84,88,95,99,122],"assumption":[17],"of":[18,45,110],"conditional":[19],"independence":[20],"in":[21,49,65],"this":[22,66],"does":[24],"not":[25],"conform":[26],"objective":[28],"reality":[29],"which":[30],"affects":[31],"its":[32],"performance":[34,44],"some":[36],"extent.":[37],"In":[38],"order":[39],"improve":[41],"text":[50,55,75,108,112,129],"categorization,":[51],"based":[58],"on":[59],"TF-IDF":[60,96],"attribute":[61],"weighting":[62],"proposed":[64],"paper.":[67],"We":[68],"use":[69],"\u03c72":[71],"statistic":[72],"extract":[74],"features":[76],"before":[77],"starts,":[80],"then":[82],"assign":[83],"different":[85,89],"weights":[86],"feature":[90],"word":[91],"sets":[92],"according":[93],"method.":[97],"Finally,":[98],"improved":[100],"algorithm,":[103],"TFIDFMNB,":[104],"used":[106,127],"for":[107,128],"test":[111],"sets.":[113],"The":[114],"experimental":[115],"comparison":[116],"analysis":[118],"results":[119],"show":[120],"that":[121],"TFIDFMNB":[123],"can":[125],"be":[126],"well.":[131]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}