{"id":"https://openalex.org/W1975258157","doi":"https://doi.org/10.1145/2517288.2517299","title":"The Microsoft academic search dataset and KDD Cup 2013","display_name":"The Microsoft academic search dataset and KDD Cup 2013","publication_year":2013,"publication_date":"2013-08-11","ids":{"openalex":"https://openalex.org/W1975258157","doi":"https://doi.org/10.1145/2517288.2517299","mag":"1975258157"},"language":"en","primary_location":{"id":"doi:10.1145/2517288.2517299","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2517288.2517299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 KDD Cup 2013 Workshop","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/A5009377962","display_name":"Senjuti Basu Roy","orcid":"https://orcid.org/0000-0003-3475-8138"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I4210150356","display_name":"University of Washington Tacoma","ror":"https://ror.org/05n8t2628","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701","https://openalex.org/I4210150356"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Senjuti Basu Roy","raw_affiliation_strings":["University of Washington, Tacoma, WA","University of Washington Tacoma, WA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Washington, Tacoma, WA","institution_ids":["https://openalex.org/I4210150356"]},{"raw_affiliation_string":"University of Washington Tacoma, WA#TAB#","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056749857","display_name":"Martine De Cock","orcid":"https://orcid.org/0000-0001-7917-0771"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Martine De Cock","raw_affiliation_strings":["Ghent University, Gent, Belgium","Ghent University , Gent, Belgium"],"affiliations":[{"raw_affiliation_string":"Ghent University, Gent, Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"Ghent University , Gent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043260495","display_name":"Vani Mandava","orcid":"https://orcid.org/0000-0003-3592-9453"},"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":"Vani Mandava","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030835807","display_name":"Swapna Savanna","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I4210150356","display_name":"University of Washington Tacoma","ror":"https://ror.org/05n8t2628","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701","https://openalex.org/I4210150356"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Swapna Savanna","raw_affiliation_strings":["University of Washington, Tacoma, WA","University of Washington Tacoma, WA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Washington, Tacoma, WA","institution_ids":["https://openalex.org/I4210150356"]},{"raw_affiliation_string":"University of Washington Tacoma, WA#TAB#","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012872167","display_name":"B D'Alessandro","orcid":"https://orcid.org/0000-0002-0050-401X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brian Dalessandro","raw_affiliation_strings":["Media6Degrees, New York, NY"],"affiliations":[{"raw_affiliation_string":"Media6Degrees, New York, NY","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003651471","display_name":"Claudia Perlich","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Claudia Perlich","raw_affiliation_strings":["Media6Degrees, New York, NY"],"affiliations":[{"raw_affiliation_string":"Media6Degrees, New York, NY","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006167480","display_name":"William Cukierski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"William Cukierski","raw_affiliation_strings":["Kaggle, Millington, NJ"],"affiliations":[{"raw_affiliation_string":"Kaggle, Millington, NJ","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049495063","display_name":"Ben Hamner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ben Hamner","raw_affiliation_strings":["Kaggle, San Francisco, CA"],"affiliations":[{"raw_affiliation_string":"Kaggle, San Francisco, CA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5009377962"],"corresponding_institution_ids":["https://openalex.org/I201448701","https://openalex.org/I4210150356"],"apc_list":null,"apc_paid":null,"fwci":8.5315,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.97622373,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9958999752998352,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9958999752998352,"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"}},{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9898999929428101,"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/computer-science","display_name":"Computer science","score":0.7894830703735352},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.7094087600708008},{"id":"https://openalex.org/keywords/snapshot","display_name":"Snapshot (computer storage)","score":0.6509090065956116},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5460999608039856},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5268971920013428},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.4874916076660156},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3858572840690613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3581048846244812},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.35281866788864136},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.15380516648292542}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7894830703735352},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.7094087600708008},{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.6509090065956116},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5460999608039856},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5268971920013428},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.4874916076660156},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3858572840690613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3581048846244812},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35281866788864136},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.15380516648292542},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2517288.2517299","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2517288.2517299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 KDD Cup 2013 Workshop","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.397.6154","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.397.6154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.kdd.org/kddcup2013/sites/default/files/papers/papers.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":2,"referenced_works":["https://openalex.org/W1532325895","https://openalex.org/W4290864872"],"related_works":["https://openalex.org/W2353179089","https://openalex.org/W2923538289","https://openalex.org/W2353125546","https://openalex.org/W2542847180","https://openalex.org/W2470643824","https://openalex.org/W4400595174","https://openalex.org/W2349635380","https://openalex.org/W4353089801","https://openalex.org/W2353819554","https://openalex.org/W3034994054"],"abstract_inverted_index":{"KDD":[0],"Cup":[1],"2013":[2,42],"challenged":[3],"participants":[4],"to":[5,53,73],"tackle":[6],"the":[7,117,120,125,155,158,160,164],"problem":[8,156],"of":[9,17,23,35,119,131],"author":[10,59,67,76],"name":[11],"ambiguity":[12],"in":[13,40,57],"a":[14,33,65,96,108],"digital":[15],"library":[16],"scientific":[18],"publications.":[19],"The":[20],"competition":[21],"consisted":[22],"two":[24],"tracks,":[25],"which":[26,55,137],"were":[27,51,85],"based":[28],"on":[29,88,101],"large-scale":[30],"datasets":[31],"from":[32,147],"snapshot":[34],"Microsoft":[36],"Academic":[37],"Search,":[38],"taken":[39],"January":[41],"and":[43,47,82,91,163],"including":[44],"250K":[45],"authors":[46],"2.5M":[48],"papers.":[49],"Participants":[50],"asked":[52],"determine":[54],"papers":[56],"an":[58,141],"profile":[60],"are":[61],"truly":[62],"written":[63],"by":[64],"given":[66],"(track":[68,78],"1),":[69],"as":[70,72,140],"well":[71],"identify":[74],"duplicate":[75],"profiles":[77],"2).":[79],"Track":[80,135],"1":[81,107],"track":[83,106,123],"2":[84],"launched":[86],"respectively":[87],"April":[89,92],"18":[90],"20,":[93],"2013,":[94],"with":[95,111],"common":[97],"final":[98],"submission":[99],"deadline":[100],"June":[102],"12,":[103],"2013.":[104],"For":[105],"training":[109],"dataset":[110],"correct":[112],"labels":[113],"was":[114,124,138],"diclosed":[115],"at":[116],"start":[118],"competition.":[121],"This":[122,150],"most":[126],"popular":[127],"one,":[128],"attracting":[129],"submissions":[130,146],"561":[132],"different":[133],"teams.":[134],"2,":[136],"formulated":[139],"unsupervised":[142],"learning":[143],"task,":[144],"received":[145],"241":[148],"participants.":[149],"paper":[151],"presents":[152],"details":[153],"about":[154],"definitions,":[157],"datasets,":[159],"evaluation":[161],"metrics":[162],"results.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":10}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
