{"id":"https://openalex.org/W2161141281","doi":"https://doi.org/10.3115/1118693.1118719","title":"Manipulating large corpora for text classification","display_name":"Manipulating large corpora for text classification","publication_year":2002,"publication_date":"2002-01-01","ids":{"openalex":"https://openalex.org/W2161141281","doi":"https://doi.org/10.3115/1118693.1118719","mag":"2161141281"},"language":"en","primary_location":{"id":"doi:10.3115/1118693.1118719","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118693.1118719","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1118719&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL-02 conference on Empirical methods in natural language processing  - EMNLP '02","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=1118719&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079605672","display_name":"Fumiyo Fukumoto","orcid":"https://orcid.org/0000-0001-7858-6206"},"institutions":[{"id":"https://openalex.org/I66906201","display_name":"University of Yamanashi","ror":"https://ror.org/059x21724","country_code":"JP","type":"education","lineage":["https://openalex.org/I66906201"]},{"id":"https://openalex.org/I44892455","display_name":"Takeda (Japan)","ror":"https://ror.org/04hjbmv12","country_code":"JP","type":"company","lineage":["https://openalex.org/I44892455"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Fumiyo Fukumoto","raw_affiliation_strings":["Department of Computer Science and Media Engineering, Yamanashi University 4-3-11 Takeda, Kofu 400-8511 Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Media Engineering, Yamanashi University 4-3-11 Takeda, Kofu 400-8511 Japan","institution_ids":["https://openalex.org/I66906201","https://openalex.org/I44892455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003025940","display_name":"Yoshimi Suzuki","orcid":"https://orcid.org/0000-0001-5466-7351"},"institutions":[{"id":"https://openalex.org/I66906201","display_name":"University of Yamanashi","ror":"https://ror.org/059x21724","country_code":"JP","type":"education","lineage":["https://openalex.org/I66906201"]},{"id":"https://openalex.org/I44892455","display_name":"Takeda (Japan)","ror":"https://ror.org/04hjbmv12","country_code":"JP","type":"company","lineage":["https://openalex.org/I44892455"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshimi Suzuki","raw_affiliation_strings":["Department of Computer Science and Media Engineering, Yamanashi University 4-3-11 Takeda, Kofu 400-8511 Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Media Engineering, Yamanashi University 4-3-11 Takeda, Kofu 400-8511 Japan","institution_ids":["https://openalex.org/I66906201","https://openalex.org/I44892455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5079605672"],"corresponding_institution_ids":["https://openalex.org/I44892455","https://openalex.org/I66906201"],"apc_list":null,"apc_paid":null,"fwci":0.8523,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.79706173,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"10","issue":null,"first_page":"196","last_page":"203"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9970999956130981,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9962000250816345,"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":0.8133656978607178},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.7971430420875549},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6809024214744568},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.6679861545562744},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6007781624794006},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5843237638473511},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5777620077133179},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.5214316844940186},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5078914761543274},{"id":"https://openalex.org/keywords/structured-support-vector-machine","display_name":"Structured support vector machine","score":0.43240487575531006},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4112424850463867},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39480671286582947},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36296260356903076},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1080818772315979},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07196745276451111}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8133656978607178},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.7971430420875549},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6809024214744568},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.6679861545562744},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6007781624794006},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5843237638473511},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5777620077133179},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.5214316844940186},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5078914761543274},{"id":"https://openalex.org/C125168437","wikidata":"https://www.wikidata.org/wiki/Q7625184","display_name":"Structured support vector machine","level":3,"score":0.43240487575531006},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4112424850463867},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39480671286582947},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36296260356903076},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1080818772315979},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07196745276451111},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/1118693.1118719","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118693.1118719","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1118719&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL-02 conference on Empirical methods in natural language processing  - EMNLP '02","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.5.5024","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.5.5024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/W/W02/W02-1026.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1118693.1118719","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118693.1118719","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1118719&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL-02 conference on Empirical methods in natural language processing  - EMNLP '02","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309102","display_name":"City University of New York","ror":"https://ror.org/00453a208"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2161141281.pdf","grobid_xml":"https://content.openalex.org/works/W2161141281.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1522263329","https://openalex.org/W1523949738","https://openalex.org/W1534477342","https://openalex.org/W1620204465","https://openalex.org/W2005422315","https://openalex.org/W2034953016","https://openalex.org/W2035754578","https://openalex.org/W2063862666","https://openalex.org/W2064580901","https://openalex.org/W2112076978","https://openalex.org/W2126502509","https://openalex.org/W2135293965","https://openalex.org/W2149684865","https://openalex.org/W2156632403","https://openalex.org/W2156909104","https://openalex.org/W2170654002","https://openalex.org/W2282078507","https://openalex.org/W4206686222","https://openalex.org/W4242870862"],"related_works":["https://openalex.org/W3125750421","https://openalex.org/W2394466068","https://openalex.org/W1987683558","https://openalex.org/W68147753","https://openalex.org/W2726838704","https://openalex.org/W2949765904","https://openalex.org/W4306949324","https://openalex.org/W4388544318","https://openalex.org/W1577730984","https://openalex.org/W2357114597"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"address":[4],"the":[5,41,51,60,64,91,100],"problem":[6],"of":[7,13,43,53,102],"dealing":[8],"with":[9],"a":[10,17,47],"large":[11,68],"collection":[12],"data":[14,24,81],"and":[15,33],"propose":[16],"method":[18],"for":[19,82,105],"text":[20],"classification":[21,106],"which":[22,49,71,94],"manipulates":[23],"using":[25,86],"two":[26],"well-known":[27],"machine":[28],"learning":[29],"techniques,":[30],"Naive":[31],"Bayes(NB)":[32],"Support":[34],"Vector":[35],"Machines(SVMs).":[36],"NB":[37,87],"is":[38],"based":[39],"on":[40,59],"assumption":[42],"word":[44],"independence":[45],"in":[46],"text,":[48],"makes":[50,72,95],"computation":[52,103],"it":[54,73,96],"far":[55],"more":[56],"efficient.":[57],"SVMs,":[58],"other":[61],"hand,":[62],"have":[63],"potential":[65],"to":[66,75,90,98],"handle":[67],"feature":[69],"spaces,":[70],"possible":[74,97],"produce":[76],"better":[77],"performance.":[78],"The":[79],"training":[80],"SVMs":[83],"are":[84],"extracted":[85],"classifiers":[88],"according":[89],"category":[92],"hierarchies,":[93],"reduce":[99],"amount":[101],"necessary":[104],"without":[107],"sacrificing":[108],"accuracy.":[109]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}