{"id":"https://openalex.org/W2043499927","doi":"https://doi.org/10.1145/1989323.1989406","title":"Mining a search engine's corpus","display_name":"Mining a search engine's corpus","publication_year":2011,"publication_date":"2011-06-12","ids":{"openalex":"https://openalex.org/W2043499927","doi":"https://doi.org/10.1145/1989323.1989406","mag":"2043499927"},"language":"en","primary_location":{"id":"doi:10.1145/1989323.1989406","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1989323.1989406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 ACM SIGMOD International Conference on Management of data","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/A5100432807","display_name":"Mingyang Zhang","orcid":"https://orcid.org/0000-0001-7084-6237"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mingyang Zhang","raw_affiliation_strings":["George Washington University, Washington, DC, USA"],"affiliations":[{"raw_affiliation_string":"George Washington University, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100331345","display_name":"Nan Zhang","orcid":"https://orcid.org/0009-0001-0255-8484"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nan Zhang","raw_affiliation_strings":["George Washington University, Washington, DC, USA"],"affiliations":[{"raw_affiliation_string":"George Washington University, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002203026","display_name":"Gautam Das","orcid":"https://orcid.org/0000-0002-4627-9065"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gautam Das","raw_affiliation_strings":["University of Texas at Arlington, Arlington, TX, USA","[University of Texas at Arlington, Arlington, TX, USA]"],"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]},{"raw_affiliation_string":"[University of Texas at Arlington, Arlington, TX, USA]","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100432807"],"corresponding_institution_ids":["https://openalex.org/I193531525"],"apc_list":null,"apc_paid":null,"fwci":3.6747,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.93692195,"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":"793","last_page":"804"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9818000197410583,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9818000197410583,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9726999998092651,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9714000225067139,"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":0.85023033618927},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.7657880783081055},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.6444528102874756},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6220138669013977},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.5987572073936462},{"id":"https://openalex.org/keywords/search-analytics","display_name":"Search analytics","score":0.5448046922683716},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.520497739315033},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.500136137008667},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.48786044120788574},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.47311660647392273},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4388878345489502},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.42261236906051636},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.06828474998474121}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.85023033618927},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.7657880783081055},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.6444528102874756},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6220138669013977},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.5987572073936462},{"id":"https://openalex.org/C14838553","wikidata":"https://www.wikidata.org/wiki/Q7441639","display_name":"Search analytics","level":4,"score":0.5448046922683716},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.520497739315033},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.500136137008667},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.48786044120788574},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.47311660647392273},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4388878345489502},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.42261236906051636},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.06828474998474121},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1989323.1989406","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1989323.1989406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1573859446","https://openalex.org/W1586176254","https://openalex.org/W1586825695","https://openalex.org/W1604437383","https://openalex.org/W1605217017","https://openalex.org/W1986828474","https://openalex.org/W1989856433","https://openalex.org/W2018816493","https://openalex.org/W2041771431","https://openalex.org/W2081948558","https://openalex.org/W2102815161","https://openalex.org/W2125638313","https://openalex.org/W2128941908","https://openalex.org/W2129817180","https://openalex.org/W2131006463","https://openalex.org/W2136059419","https://openalex.org/W6635193281","https://openalex.org/W6723958736"],"related_works":["https://openalex.org/W2096359267","https://openalex.org/W2901901036","https://openalex.org/W2026738364","https://openalex.org/W1521725692","https://openalex.org/W2093300859","https://openalex.org/W3008917487","https://openalex.org/W2124814993","https://openalex.org/W2013069866","https://openalex.org/W3197639690","https://openalex.org/W2572349046"],"abstract_inverted_index":{"Search":[0],"engines":[1,12],"over":[2,13,20,61],"document":[3],"corpora":[4],"typically":[5],"provide":[6],"keyword-search":[7,96],"interfaces.":[8],"Examples":[9],"include":[10],"search":[11,30,52,63],"the":[14,45,73,81,95,124,165,177],"web":[15],"as":[16,18,123,145,147],"well":[17,146],"those":[19],"enterprise":[21],"and":[22,80,106,127,172],"government":[23],"websites.":[24],"The":[25],"corpus":[26],"of":[27,36,38,75,85,92,161,179],"such":[28],"a":[29,33,62,89,120,156],"engine":[31],"forms":[32],"rich":[34],"source":[35],"information":[37],"analytical":[39],"interest":[40],"to":[41,68,175],"third":[42],"parties,":[43],"but":[44],"only":[46],"available":[47],"access":[48],"is":[49],"by":[50],"issuing":[51,88],"queries":[53,93],"through":[54,94],"its":[55],"interface.":[56],"To":[57],"support":[58],"data":[59],"analytics":[60],"engine's":[64],"corpus,":[65],"one":[66],"needs":[67],"address":[69],"two":[70],"main":[71],"problems,":[72],"sampling":[74,100],"documents":[76],"(for":[77],"offline":[78],"analytics)":[79],"direct":[82],"(online)":[83],"estimation":[84,116,125],"aggregates,":[86],"while":[87,154],"small":[90,152],"number":[91],"interface.Existing":[97],"work":[98],"on":[99],"produces":[101],"samples":[102,144],"with":[103,151],"unknown":[104],"bias":[105],"may":[107],"incur":[108],"an":[109,159],"extremely":[110],"high":[111],"query":[112,128,157],"cost.":[113],"Existing":[114],"aggregate":[115,149],"technique":[117],"suffers":[118],"from":[119],"similar":[121],"problem,":[122],"error":[126],"cost":[129,158],"can":[130],"both":[131],"be":[132],"large":[133],"for":[134],"certain":[135],"aggregates.":[136],"We":[137,168],"propose":[138],"novel":[139],"techniques":[140],"which":[141],"produce":[142],"unbiased":[143,148],"estimates":[150],"variances":[153],"incurring":[155],"order":[160],"magnitude":[162],"smaller":[163],"than":[164],"existing":[166],"techniques.":[167],"present":[169],"theoretical":[170],"analysis":[171],"extensive":[173],"experiments":[174],"illustrate":[176],"effectiveness":[178],"our":[180],"approach.":[181]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}