{"id":"https://openalex.org/W2108828123","doi":"https://doi.org/10.1145/1244002.1244096","title":"Using hypothesis margin to boost centroid text classifier","display_name":"Using hypothesis margin to boost centroid text classifier","publication_year":2007,"publication_date":"2007-03-11","ids":{"openalex":"https://openalex.org/W2108828123","doi":"https://doi.org/10.1145/1244002.1244096","mag":"2108828123"},"language":"en","primary_location":{"id":"doi:10.1145/1244002.1244096","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1244002.1244096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2007 ACM symposium on Applied computing","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/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":"funder","lineage":["https://openalex.org/I19820366"]},{"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":true,"raw_author_name":"Songbo Tan","raw_affiliation_strings":["ICT, Beijing, China","ict, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"ICT, Beijing, China","institution_ids":["https://openalex.org/I4210101410"]},{"raw_affiliation_string":"ict, Beijing, China#TAB#","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029998682","display_name":"Xueqi Cheng","orcid":"https://orcid.org/0000-0002-5201-8195"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"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","ict, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"ICT, Beijing, China","institution_ids":["https://openalex.org/I4210101410"]},{"raw_affiliation_string":"ict, Beijing, China#TAB#","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100511387"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210101410"],"apc_list":null,"apc_paid":null,"fwci":0.483,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.76384098,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"143","issue":null,"first_page":"398","last_page":"403"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9957000017166138,"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":0.9944000244140625,"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/centroid","display_name":"Centroid","score":0.8315567374229431},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7586197853088379},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.698911726474762},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6367934942245483},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6365196704864502},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5816265940666199},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5657636523246765},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5447018146514893},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5416567325592041},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.49738219380378723},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4496746361255646},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.43573620915412903},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.322867214679718}],"concepts":[{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.8315567374229431},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7586197853088379},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.698911726474762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6367934942245483},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6365196704864502},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5816265940666199},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5657636523246765},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5447018146514893},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5416567325592041},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.49738219380378723},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4496746361255646},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43573620915412903},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.322867214679718},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1244002.1244096","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1244002.1244096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2007 ACM symposium on Applied computing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.498.8278","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.498.8278","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/SAC07-Hypothesis Margin.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.550000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W99080471","https://openalex.org/W1514800236","https://openalex.org/W1550206324","https://openalex.org/W1924689489","https://openalex.org/W1972640883","https://openalex.org/W1972907467","https://openalex.org/W1975846642","https://openalex.org/W1978394996","https://openalex.org/W1979495886","https://openalex.org/W1982718731","https://openalex.org/W1993934121","https://openalex.org/W2005422315","https://openalex.org/W2009276147","https://openalex.org/W2015932775","https://openalex.org/W2040424159","https://openalex.org/W2053463056","https://openalex.org/W2060216474","https://openalex.org/W2071664212","https://openalex.org/W2096152098","https://openalex.org/W2114535528","https://openalex.org/W2118020653","https://openalex.org/W2119821739","https://openalex.org/W2146077544","https://openalex.org/W2149684865","https://openalex.org/W2150067374","https://openalex.org/W2435251607","https://openalex.org/W4245322178"],"related_works":["https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2366793250","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":{"Centroid":[0,68],"Classifier":[1],"is":[2,60],"a":[3,66],"simple":[4],"and":[5,62],"yet":[6],"efficient":[7],"method":[8,82],"for":[9],"text":[10],"categorization.":[11],"However":[12],"it":[13,96],"often":[14],"suffers":[15],"from":[16],"the":[17],"inductive":[18],"bias":[19],"or":[20],"model":[21],"misfit":[22],"incurred":[23],"by":[24],"its":[25],"assumption.":[26],"In":[27],"order":[28],"to":[29,64,85],"address":[30],"this":[31],"issue,":[32],"training-set":[33,38],"errors":[34],"as":[35,37,42,92,94],"well":[36,93],"margins":[39],"are":[40],"regarded":[41],"training":[43,58],"criterions.":[44],"Based":[45],"on":[46,75],"these":[47],"two":[48],"criterions,":[49],"an":[50],"overall":[51],"(or":[52],"global)":[53],"objective":[54],"function":[55],"over":[56],"all":[57],"examples":[59],"constructed,":[61],"optimized":[63],"produce":[65],"refined":[67],"classification":[69],"model.":[70],"The":[71],"empirical":[72],"assessment":[73],"conducted":[74],"four":[76],"benchmark":[77],"collections":[78],"evidence":[79],"that":[80],"proposed":[81],"performs":[83],"comparably":[84],"state-of-the-art":[86],"SVM":[87],"classifier":[88],"in":[89,97],"classifying":[90],"performance,":[91],"beats":[95],"running":[98],"time.":[99]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}