{"id":"https://openalex.org/W2130887095","doi":"https://doi.org/10.1145/1557019.1557143","title":"Improving classification accuracy using automatically extracted training data","display_name":"Improving classification accuracy using automatically extracted training data","publication_year":2009,"publication_date":"2009-06-28","ids":{"openalex":"https://openalex.org/W2130887095","doi":"https://doi.org/10.1145/1557019.1557143","mag":"2130887095"},"language":"en","primary_location":{"id":"doi:10.1145/1557019.1557143","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1557019.1557143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining","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/A5017633018","display_name":"Ariel Fuxman","orcid":"https://orcid.org/0009-0003-6760-997X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ariel Fuxman","raw_affiliation_strings":["Microsoft Research, Mountain View, CA, USA","Microsoft Research, Mountain View, CA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, Mountain View, CA, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103559059","display_name":"Anitha Kannan","orcid":"https://orcid.org/0000-0003-3028-4959"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anitha Kannan","raw_affiliation_strings":["Microsoft Research, Mountain View, CA, USA","Microsoft Research, Mountain View, CA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, Mountain View, CA, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067065279","display_name":"Andrew B. Goldberg","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew B. Goldberg","raw_affiliation_strings":["Univ. of Wisconsin-Madison, Madison, WI, USA","University of Wisconsin- Madison Madison WI USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Wisconsin-Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]},{"raw_affiliation_string":"University of Wisconsin- Madison Madison WI USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071177661","display_name":"Rakesh Agrawal","orcid":"https://orcid.org/0000-0002-6746-9829"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rakesh Agrawal","raw_affiliation_strings":["Microsoft Research, Mountain View, CA, USA","Microsoft Research, Mountain View, CA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, Mountain View, CA, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066962453","display_name":"Panayiotis Tsaparas","orcid":"https://orcid.org/0000-0002-3490-1507"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Panayiotis Tsaparas","raw_affiliation_strings":["Microsoft Research, Mountain View, CA, USA","Microsoft Research, Mountain View, CA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, Mountain View, CA, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113541478","display_name":"John Shafer","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Shafer","raw_affiliation_strings":["Microsoft Research, Mountain View, CA, USA","Microsoft Research, Mountain View, CA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, Mountain View, CA, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7059,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.85493367,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1145","last_page":"1154"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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/T11719","display_name":"Data Quality and Management","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8695918321609497},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.6728709936141968},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5939393639564514},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5626987218856812},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5016107559204102},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.484881728887558},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4566861391067505},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.45399293303489685},{"id":"https://openalex.org/keywords/co-training","display_name":"Co-training","score":0.4354996383190155},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.41190972924232483},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3209187984466553},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.12175160646438599}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8695918321609497},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.6728709936141968},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5939393639564514},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5626987218856812},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5016107559204102},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.484881728887558},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4566861391067505},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.45399293303489685},{"id":"https://openalex.org/C2776959682","wikidata":"https://www.wikidata.org/wiki/Q17005296","display_name":"Co-training","level":3,"score":0.4354996383190155},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41190972924232483},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3209187984466553},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.12175160646438599},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1557019.1557143","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1557019.1557143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.187.9407","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.187.9407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/pubs/80763/CommerceIntent_KDD09.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.217.329","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.217.329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.wisc.edu/~goldberg/publications/CommerceIntent_KDD09.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.329.8298","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.329.8298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cc.gatech.edu/~zha/CSE8801/query-annotation/p1145-fuxman.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1595276678","https://openalex.org/W1602389404","https://openalex.org/W1666146316","https://openalex.org/W1957763477","https://openalex.org/W1974360117","https://openalex.org/W1978658266","https://openalex.org/W1983599491","https://openalex.org/W1994563080","https://openalex.org/W2000577984","https://openalex.org/W2000826169","https://openalex.org/W2047221353","https://openalex.org/W2099111195","https://openalex.org/W2101210369","https://openalex.org/W2113455164","https://openalex.org/W2136504847","https://openalex.org/W2157963512","https://openalex.org/W2163375626","https://openalex.org/W6640945468"],"related_works":["https://openalex.org/W2797776314","https://openalex.org/W4303683898","https://openalex.org/W1505796919","https://openalex.org/W2104788210","https://openalex.org/W2130553454","https://openalex.org/W121244246","https://openalex.org/W2766321935","https://openalex.org/W3183551524","https://openalex.org/W2363068571","https://openalex.org/W1459710595"],"abstract_inverted_index":{"Classification":[0],"is":[1,53],"a":[2,24,43,48],"core":[3],"task":[4],"in":[5,18,70],"knowledge":[6],"discovery":[7],"and":[8,11,73],"data":[9,67,77],"mining,":[10],"there":[12],"has":[13],"been":[14,85],"substantial":[15],"research":[16],"effort":[17],"developing":[19],"sophisticated":[20,49],"classification":[21],"models.":[22],"In":[23,63],"parallel":[25],"thread,":[26],"recent":[27],"work":[28],"from":[29],"the":[30],"NLP":[31],"community":[32],"suggests":[33],"that":[34],"for":[35],"tasks":[36],"such":[37],"as":[38],"natural":[39],"language":[40],"disambiguation":[41],"even":[42],"simple":[44],"algorithm":[45],"can":[46],"outperform":[47],"one,":[50],"if":[51],"it":[52],"provided":[54],"with":[55],"large":[56],"quantities":[57],"of":[58,82],"high":[59,74],"quality":[60,75],"training":[61,66,76],"data.":[62],"those":[64],"applications,":[65],"occurs":[68],"naturally":[69],"text":[71],"corpora,":[72],"sets":[78],"running":[79],"into":[80],"billions":[81],"words":[83],"have":[84],"reportedly":[86],"used.":[87]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}