{"id":"https://openalex.org/W4407785175","doi":"https://doi.org/10.1145/3718740","title":"New Bagging Based Ensemble Learning Algorithm Distinguishing Short and Long Texts for Document Classification","display_name":"New Bagging Based Ensemble Learning Algorithm Distinguishing Short and Long Texts for Document Classification","publication_year":2025,"publication_date":"2025-02-20","ids":{"openalex":"https://openalex.org/W4407785175","doi":"https://doi.org/10.1145/3718740"},"language":"en","primary_location":{"id":"doi:10.1145/3718740","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3718740","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3718740","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100707542","display_name":"Youwei Wang","orcid":"https://orcid.org/0000-0002-3925-3422"},"institutions":[{"id":"https://openalex.org/I137867983","display_name":"Central University of Finance and Economics","ror":"https://ror.org/008e3hf02","country_code":"CN","type":"education","lineage":["https://openalex.org/I137867983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youwei Wang","raw_affiliation_strings":["Central University of Finance and Economics, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3925-3422","affiliations":[{"raw_affiliation_string":"Central University of Finance and Economics, Beijing, China","institution_ids":["https://openalex.org/I137867983"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101813002","display_name":"Lizhou Feng","orcid":"https://orcid.org/0000-0002-1010-8539"},"institutions":[{"id":"https://openalex.org/I193524592","display_name":"Tianjin University of Finance and Economics","ror":"https://ror.org/05ev1jb90","country_code":"CN","type":"education","lineage":["https://openalex.org/I193524592"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lizhou Feng","raw_affiliation_strings":["Tianjin University of Finance and Economics, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-1010-8539","affiliations":[{"raw_affiliation_string":"Tianjin University of Finance and Economics, Tianjin, China","institution_ids":["https://openalex.org/I193524592"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01183499,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"24","issue":"4","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9977999925613403,"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":0.9977999925613403,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.996999979019165,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9793999791145325,"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/ensemble-learning","display_name":"Ensemble learning","score":0.6816948652267456},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6086831092834473},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6037415266036987},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5028175711631775},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39975306391716003},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3804720938205719}],"concepts":[{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.6816948652267456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6086831092834473},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6037415266036987},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5028175711631775},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39975306391716003},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3804720938205719}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3718740","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3718740","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3718740","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3718740","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8418666056","display_name":null,"funder_award_id":"61906220","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1498305593","https://openalex.org/W1539376383","https://openalex.org/W1594880714","https://openalex.org/W1832693441","https://openalex.org/W1930624869","https://openalex.org/W1974079881","https://openalex.org/W1974844180","https://openalex.org/W1984762104","https://openalex.org/W2064675550","https://openalex.org/W2081697244","https://openalex.org/W2099454382","https://openalex.org/W2104167780","https://openalex.org/W2136903812","https://openalex.org/W2140785063","https://openalex.org/W2170413589","https://openalex.org/W2309693750","https://openalex.org/W2470673105","https://openalex.org/W2517194566","https://openalex.org/W2529550020","https://openalex.org/W2550143307","https://openalex.org/W2560070550","https://openalex.org/W2734773959","https://openalex.org/W2740721704","https://openalex.org/W2743537871","https://openalex.org/W2799236921","https://openalex.org/W2896457183","https://openalex.org/W2897100137","https://openalex.org/W2914767245","https://openalex.org/W2919821184","https://openalex.org/W2981613521","https://openalex.org/W2990625131","https://openalex.org/W3004993122","https://openalex.org/W3014252901","https://openalex.org/W3023462908","https://openalex.org/W3035568641","https://openalex.org/W3048836559","https://openalex.org/W3129439996","https://openalex.org/W3162005827","https://openalex.org/W3190231162","https://openalex.org/W4212883601","https://openalex.org/W4220726338","https://openalex.org/W4236137412","https://openalex.org/W4239510810","https://openalex.org/W4292382515","https://openalex.org/W6719819555","https://openalex.org/W6739901393","https://openalex.org/W6754884518"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"To":[0],"improve":[1,91,163],"the":[2,27,44,57,79,92,99,111,116,126,133,142,145,150,159,164],"classification":[3,23,64,97,118,168],"accuracy":[4,165],"of":[5,29,81,101,166],"ensemble":[6,13,138,179],"learning,":[7],"a":[8,69],"new":[9],"bootstrap":[10],"aggregating":[11],"(Bagging)":[12],"learning":[14,33,176,180],"algorithm":[15,160],"distinguishing":[16],"short":[17,39,51,84,104],"and":[18,38,43,50,68,83,96,103,125,169,178],"long":[19,37,49,82,102],"texts":[20,40,52],"for":[21,48],"document":[22,167],"is":[24,66,87,107,130],"proposed.":[25,88],"First,":[26],"performances":[28],"different":[30,121],"typical":[31,174],"deep":[32,175],"methods":[34],"on":[35,120,154],"processing":[36],"are":[41,53,123],"compared,":[42],"optimal":[45],"base":[46],"classifiers":[47],"selected,":[54],"respectively.":[55],"Second,":[56],"random":[58,73],"sampling":[59,74,146],"method":[60,75,139],"in":[61],"traditional":[62,134],"Bagging":[63],"algorithms":[65,177],"improved,":[67],"threshold":[70],"group":[71],"based":[72],"that":[76,144,158],"can":[77,161],"balance":[78],"numbers":[80],"text":[85,105],"subsets":[86,106],"Moreover,":[89],"to":[90,140],"model":[93],"inference":[94],"speed":[95],"accuracy,":[98],"training":[100],"realized":[108],"by":[109],"combining":[110],"knowledge":[112],"distillation":[113],"theory.":[114],"Finally,":[115],"sample":[117],"probabilities":[119],"categories":[122],"considered,":[124],"category":[127],"similarity":[128],"information":[129],"combined":[131],"with":[132],"weighted":[135],"voting":[136],"classifier":[137],"avoid":[141],"problem":[143],"process":[147],"may":[148],"decrease":[149],"accuracy.":[151],"Experimental":[152],"results":[153],"multiple":[155],"datasets":[156],"show":[157],"effectively":[162],"has":[170],"obvious":[171],"advantages":[172],"over":[173],"algorithms.":[181]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}