{"id":"https://openalex.org/W2149776783","doi":"https://doi.org/10.1145/1099554.1099687","title":"A novel refinement approach for text categorization","display_name":"A novel refinement approach for text categorization","publication_year":2005,"publication_date":"2005-10-31","ids":{"openalex":"https://openalex.org/W2149776783","doi":"https://doi.org/10.1145/1099554.1099687","mag":"2149776783"},"language":"en","primary_location":{"id":"doi:10.1145/1099554.1099687","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1099554.1099687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100511387","display_name":"Songbo Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songbo Tan","raw_affiliation_strings":["ICT, Beijing, CHINA & Chinese Academy of Sciences, CHINA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICT, Beijing, CHINA & Chinese Academy of Sciences, CHINA","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029998682","display_name":"Xueqi Cheng","orcid":"https://orcid.org/0000-0002-5201-8195"},"institutions":[{"id":"https://openalex.org/I4210101410","display_name":"International Centre for Theoretical Physics Asia-Pacific","ror":"https://ror.org/01z2px678","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210101410","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueqi Cheng","raw_affiliation_strings":["ICT, Beijing, CHINA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICT, Beijing, CHINA","institution_ids":["https://openalex.org/I4210101410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054898062","display_name":"Moustafa Ghanem","orcid":"https://orcid.org/0000-0001-5660-4565"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Moustafa M. Ghanem","raw_affiliation_strings":["Imperial College London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108156794","display_name":"Bin Wang","orcid":"https://orcid.org/0000-0002-3790-2708"},"institutions":[{"id":"https://openalex.org/I4210101410","display_name":"International Centre for Theoretical Physics Asia-Pacific","ror":"https://ror.org/01z2px678","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210101410","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Wang","raw_affiliation_strings":["ICT, Beijing, CHINA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICT, Beijing, CHINA","institution_ids":["https://openalex.org/I4210101410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101752081","display_name":"Hongbo Xu","orcid":"https://orcid.org/0000-0002-0258-7840"},"institutions":[{"id":"https://openalex.org/I4210101410","display_name":"International Centre for Theoretical Physics Asia-Pacific","ror":"https://ror.org/01z2px678","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210101410","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbo Xu","raw_affiliation_strings":["ICT, Beijing, CHINA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICT, Beijing, CHINA","institution_ids":["https://openalex.org/I4210101410"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.9291,"has_fulltext":false,"cited_by_count":106,"citation_normalized_percentile":{"value":0.9617213,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"469","last_page":"476"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9997000098228455,"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":0.9997000098228455,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9909999966621399,"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":0.9872999787330627,"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":0.7972139716148376},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7893321514129639},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.7012975215911865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6956589818000793},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6635531187057495},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.6311177015304565},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6147014498710632},{"id":"https://openalex.org/keywords/margin-classifier","display_name":"Margin classifier","score":0.5301718711853027},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.519957423210144},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5063027143478394},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.45733529329299927},{"id":"https://openalex.org/keywords/structured-support-vector-machine","display_name":"Structured support vector machine","score":0.42628592252731323},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32605743408203125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7972139716148376},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7893321514129639},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.7012975215911865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6956589818000793},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6635531187057495},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.6311177015304565},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6147014498710632},{"id":"https://openalex.org/C173102733","wikidata":"https://www.wikidata.org/wiki/Q6760396","display_name":"Margin classifier","level":3,"score":0.5301718711853027},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.519957423210144},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5063027143478394},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.45733529329299927},{"id":"https://openalex.org/C125168437","wikidata":"https://www.wikidata.org/wiki/Q7625184","display_name":"Structured support vector machine","level":3,"score":0.42628592252731323},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32605743408203125}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1099554.1099687","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1099554.1099687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.111.7399","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.111.7399","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.i3s.ac.cn/downloads/text/novel.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.549.4327","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.549.4327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.searchforum.org.cn/tansongbo/paper/CIKM05-Refinement Approach.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W312021071","https://openalex.org/W1550206324","https://openalex.org/W1972640883","https://openalex.org/W1979495886","https://openalex.org/W2005422315","https://openalex.org/W2009276147","https://openalex.org/W2053463056","https://openalex.org/W2118020653","https://openalex.org/W2150067374","https://openalex.org/W2435251607","https://openalex.org/W4241865841"],"related_works":["https://openalex.org/W2366793250","https://openalex.org/W2384390720","https://openalex.org/W2388218200","https://openalex.org/W3142456129","https://openalex.org/W1988416745","https://openalex.org/W2316626294","https://openalex.org/W2058558406","https://openalex.org/W2371356469","https://openalex.org/W2130972437","https://openalex.org/W4253128984"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"present":[4,59],"a":[5,33,48,53,119],"novel":[6],"strategy,":[7],"DragPushing,":[8],"for":[9],"improving":[10],"the":[11,29,82,90,95,98],"performance":[12,87,96],"of":[13,23,32,64,97,110],"text":[14],"classifiers.":[15],"The":[16,75],"strategy":[17],"is":[18,40,103],"generic":[19],"and":[20,52,71],"takes":[21],"advantage":[22],"training":[24],"errors":[25],"to":[26,42,108],"successively":[27],"refine":[28],"classification":[30,46],"model":[31],"base":[34,91],"classifier.":[35],"We":[36,58],"describe":[37],"how":[38],"it":[39],"applied":[41],"generate":[43],"two":[44],"new":[45],"algorithms;":[47],"Refined":[49,54,99],"Centroid":[50,100],"Classifier":[51,101],"Na\u00efve":[55],"Bayes":[56],"Classifier.":[57],"an":[60],"extensive":[61],"experimental":[62],"evaluation":[63],"both":[65],"algorithms":[66],"on":[67],"three":[68],"English":[69],"collections":[70],"one":[72],"Chinese":[73],"corpus.":[74],"results":[76],"indicate":[77],"that":[78,109],"in":[79],"each":[80],"case,":[81],"refined":[83],"classifiers":[84,92],"achieve":[85],"significant":[86],"improvement":[88],"over":[89],"used.":[93],"Furthermore,":[94],"implemented":[102],"comparable,":[104],"if":[105],"not":[106],"better,":[107],"state-of-the-art":[111],"support":[112],"vector":[113],"machine":[114],"(SVM)-based":[115],"classifier,":[116],"but":[117],"offers":[118],"much":[120],"lower":[121],"computational":[122],"cost.":[123]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":7}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}