{"id":"https://openalex.org/W2151595407","doi":"https://doi.org/10.4304/jcp.7.12.2913-2920","title":"An Improved Random Forest Classifier for Text Categorization","display_name":"An Improved Random Forest Classifier for Text Categorization","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2151595407","doi":"https://doi.org/10.4304/jcp.7.12.2913-2920","mag":"2151595407"},"language":"en","primary_location":{"id":"doi:10.4304/jcp.7.12.2913-2920","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jcp.7.12.2913-2920","pdf_url":null,"source":{"id":"https://openalex.org/S77894049","display_name":"Journal of Computers","issn_l":"1796-203X","issn":["1796-203X"],"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 Computers","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/A5053591377","display_name":"Baoxun Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baoxun Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xiufeng Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiufeng Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002523892","display_name":"Yunming Ye","orcid":"https://orcid.org/0000-0002-1807-8581"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunming Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103340525","display_name":"Jiefeng Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiefeng Cheng","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":1.7398,"has_fulltext":false,"cited_by_count":171,"citation_normalized_percentile":{"value":0.8715205,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"7","issue":"12","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":0.9995999932289124,"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":0.9995999932289124,"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":0.989300012588501,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9886999726295471,"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/random-forest","display_name":"Random forest","score":0.8347316980361938},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6469988226890564},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6338851451873779},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5709136128425598},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5187442898750305},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.4942519962787628},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43563586473464966},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43023595213890076}],"concepts":[{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.8347316980361938},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6469988226890564},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6338851451873779},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5709136128425598},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5187442898750305},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.4942519962787628},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43563586473464966},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43023595213890076}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.4304/jcp.7.12.2913-2920","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jcp.7.12.2913-2920","pdf_url":null,"source":{"id":"https://openalex.org/S77894049","display_name":"Journal of Computers","issn_l":"1796-203X","issn":["1796-203X"],"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 Computers","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.942.5312","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.942.5312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ojs.academypublisher.com/index.php/jcp/article/download/jcp071229132920/5980/","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W140312209","https://openalex.org/W385173559","https://openalex.org/W592246762","https://openalex.org/W1500332810","https://openalex.org/W1550206324","https://openalex.org/W1570448133","https://openalex.org/W1972640883","https://openalex.org/W1982589161","https://openalex.org/W2005422315","https://openalex.org/W2043175314","https://openalex.org/W2063198646","https://openalex.org/W2071664212","https://openalex.org/W2112076978","https://openalex.org/W2149684865","https://openalex.org/W2165888424","https://openalex.org/W2469781980","https://openalex.org/W2911964244","https://openalex.org/W2976840617","https://openalex.org/W6617775479","https://openalex.org/W6651487525","https://openalex.org/W6666227452","https://openalex.org/W6668334885","https://openalex.org/W6676769703","https://openalex.org/W6732643008"],"related_works":["https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2889302474","https://openalex.org/W2390698788","https://openalex.org/W2035261173","https://openalex.org/W2138922887","https://openalex.org/W2125109223","https://openalex.org/W2383063829","https://openalex.org/W2082678934"],"abstract_inverted_index":{"Abstract":[0],"\u2014":[1,126],"This":[2,14],"paper":[3],"proposes":[4],"an":[5],"improved":[6,110],"random":[7,51,111,127,131],"forest":[8,52],"algorithm":[9,15],"for":[10,19,49,70],"classifying":[11],"text":[12,33,58,98,116,129],"data.":[13],"is":[16,32],"particularly":[17],"designed":[18],"analyzing":[20],"very":[21],"high":[22],"dimensional":[23],"data":[24,31,99],"with":[25,60,101],"multiple":[26],"classes":[27],"whose":[28],"well-known":[29],"representative":[30],"corpus.":[34],"A":[35],"novel":[36],"feature":[37,67],"weighting":[38,68],"method":[39,43,69,95],"and":[40,46,73,83],"tree":[41,74],"selection":[42,75],"are":[44],"developed":[45],"synergistically":[47],"served":[48],"making":[50],"framework":[53],"well":[54],"suited":[55],"to":[56],"categorize":[57],"documents":[59],"dozens":[61],"of":[62,121],"topics.":[63],"With":[64],"the":[65,93,114],"new":[66],"subspace":[71,81],"sampling":[72],"method,":[76],"we":[77],"can":[78],"effectively":[79],"reduce":[80],"size":[82],"improve":[84],"classification":[85,117,122],"performance":[86],"without":[87],"increasing":[88],"error":[89],"bound.":[90],"We":[91],"apply":[92],"proposed":[94],"on":[96],"six":[97],"sets":[100],"diverse":[102],"characteristics.":[103],"The":[104],"results":[105],"have":[106],"demonstrated":[107],"that":[108],"this":[109],"forests":[112],"outperformed":[113],"popular":[115],"methods":[118],"in":[119],"terms":[120],"performance.":[123],"Index":[124],"Terms":[125],"forest,":[128],"categorization,":[130]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":32},{"year":2021,"cited_by_count":26},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}