{"id":"https://openalex.org/W1989856433","doi":"https://doi.org/10.1145/1411509.1411514","title":"Random sampling from a search engine's index","display_name":"Random sampling from a search engine's index","publication_year":2008,"publication_date":"2008-10-01","ids":{"openalex":"https://openalex.org/W1989856433","doi":"https://doi.org/10.1145/1411509.1411514","mag":"1989856433"},"language":"en","primary_location":{"id":"doi:10.1145/1411509.1411514","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1411509.1411514","pdf_url":null,"source":{"id":"https://openalex.org/S118992489","display_name":"Journal of the ACM","issn_l":"0004-5411","issn":["0004-5411","1557-735X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the ACM","raw_type":"journal-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/A5054834255","display_name":"Ziv Bar-Yossef","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]},{"id":"https://openalex.org/I4210117425","display_name":"Google (Israel)","ror":"https://ror.org/02c20ys54","country_code":"IL","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210117425","https://openalex.org/I4210128969"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Ziv Bar-Yossef","raw_affiliation_strings":["Technion and Google Haifa, Haifa, Israel","Technion and Google Haifa, Haifa, Israel#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion and Google Haifa, Haifa, Israel","institution_ids":["https://openalex.org/I4210117425"]},{"raw_affiliation_string":"Technion and Google Haifa, Haifa, Israel#TAB#","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086993894","display_name":"Maxim Gurevich","orcid":"https://orcid.org/0000-0003-4693-0556"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Maxim Gurevich","raw_affiliation_strings":["Technion, Haifa, Israel","Technion , Haifa , Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"Technion , Haifa , Israel","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5054834255"],"corresponding_institution_ids":["https://openalex.org/I174306211","https://openalex.org/I4210117425"],"apc_list":null,"apc_paid":null,"fwci":15.2729,"has_fulltext":false,"cited_by_count":113,"citation_normalized_percentile":{"value":0.9890846,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"55","issue":"5","first_page":"1","last_page":"74"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9976999759674072,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9976999759674072,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9926000237464905,"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/T11106","display_name":"Data Management and Algorithms","score":0.9922000169754028,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.6827170848846436},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6664244532585144},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6133557558059692},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.6102368831634521},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.49625688791275024},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.49072444438934326},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4766588807106018},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.4755932092666626},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.42999377846717834},{"id":"https://openalex.org/keywords/random-walk","display_name":"Random walk","score":0.42853233218193054},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2959485650062561},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.29499268531799316},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23037183284759521}],"concepts":[{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.6827170848846436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6664244532585144},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6133557558059692},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.6102368831634521},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.49625688791275024},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49072444438934326},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4766588807106018},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.4755932092666626},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.42999377846717834},{"id":"https://openalex.org/C121194460","wikidata":"https://www.wikidata.org/wiki/Q856741","display_name":"Random walk","level":2,"score":0.42853233218193054},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2959485650062561},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.29499268531799316},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23037183284759521},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1411509.1411514","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1411509.1411514","pdf_url":null,"source":{"id":"https://openalex.org/S118992489","display_name":"Journal of the ACM","issn_l":"0004-5411","issn":["0004-5411","1557-735X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the ACM","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.4535","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.4535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ee.technion.ac.il/people/zivby/papers/se/se.journal.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W109881820","https://openalex.org/W1510634602","https://openalex.org/W1568495775","https://openalex.org/W1598759141","https://openalex.org/W1605217017","https://openalex.org/W1659541576","https://openalex.org/W1964038241","https://openalex.org/W1981745143","https://openalex.org/W1983416950","https://openalex.org/W2001351653","https://openalex.org/W2019473674","https://openalex.org/W2022261649","https://openalex.org/W2028716813","https://openalex.org/W2033057584","https://openalex.org/W2033747448","https://openalex.org/W2056760934","https://openalex.org/W2057767944","https://openalex.org/W2069739265","https://openalex.org/W2080676333","https://openalex.org/W2091082553","https://openalex.org/W2117850397","https://openalex.org/W2122141283","https://openalex.org/W2125125501","https://openalex.org/W2134711723","https://openalex.org/W2136059419","https://openalex.org/W2138309709","https://openalex.org/W2139964991","https://openalex.org/W2144959234","https://openalex.org/W2147164982","https://openalex.org/W2154707336","https://openalex.org/W2155711776","https://openalex.org/W2247055361","https://openalex.org/W2331283040","https://openalex.org/W2993862185","https://openalex.org/W3137614770","https://openalex.org/W4301668410","https://openalex.org/W6645817467","https://openalex.org/W6668080254","https://openalex.org/W6681574511","https://openalex.org/W7073777567"],"related_works":["https://openalex.org/W2366230866","https://openalex.org/W2357906747","https://openalex.org/W2372895414","https://openalex.org/W2386767533","https://openalex.org/W2991344826","https://openalex.org/W4308351548","https://openalex.org/W2042102171","https://openalex.org/W2279910992","https://openalex.org/W2377503869","https://openalex.org/W2381933782"],"abstract_inverted_index":{"We":[0,155,221],"revisit":[1],"a":[2,10,25,36,56,72,76,91,198],"problem":[3],"introduced":[4],"by":[5,24,90],"Bharat":[6,51],"and":[7,52,75,133,168,208,237],"Broder":[8,53],"almost":[9],"decade":[11],"ago:":[12],"How":[13],"to":[14,108,117,141,147,175,225],"sample":[15,87],"random":[16,77],"pages":[17],"from":[18,55,179],"the":[19,30,103,130,134,158,180,230,233],"corpus":[20,199],"of":[21,50,160,186,193,200,232],"documents":[22,203],"indexed":[23],"search":[26,31,46,142,181,239],"engine,":[27],"using":[28],"only":[29,153],"engine's":[32,182],"public":[33],"interface?":[34],"Such":[35],"primitive":[37],"is":[38,88],"particularly":[39],"useful":[40],"in":[41,100],"creating":[42],"objective":[43],"benchmarks":[44],"for":[45],"engines.":[47,240],"The":[48,98,138],"technique":[49],"suffers":[54],"well-recorded":[57],"bias:":[58],"it":[59],"favors":[60],"long":[61,219],"documents.":[62,220],"In":[63],"this":[64,113],"article":[65],"we":[66,115],"introduce":[67],"two":[68],"novel":[69],"sampling":[70,125,128],"algorithms:":[71],"lexicon-based":[73],"algorithm":[74],"walk":[78],"algorithm.":[79],"Our":[80,184],"algorithms":[81,146,172,212,224],"produce":[82,176],"biased":[83],"samples,":[84,99],"but":[85],"each":[86],"accompanied":[89],"weight":[92],",":[93,126,129],"which":[94],"represents":[95],"its":[96],"bias.":[97],"conjunction":[101],"with":[102],"weights,":[104],"are":[105,152,173],"then":[106],"used":[107],"simulate":[109],"near-uniform":[110,177],"samples.":[111],"To":[112],"end,":[114],"resort":[116],"four":[118],"well-known":[119],"Monte":[120,165,188],"Carlo":[121,166,189],"simulation":[122],"methods:":[123],"rejection":[124],"importance":[127],"Metropolis--Hastings":[131],"algorithm,":[132],"Maximum":[135],"Degree":[136],"method.":[137],"limited":[139],"access":[140],"engines":[143],"force":[144],"our":[145,171,205,211,223],"use":[148,222],"bias":[149,162,217],"weights":[150,163],"that":[151,170,210],"\u201capproximate\u201d.":[154],"characterize":[156],"analytically":[157],"effect":[159],"approximate":[161,187],"on":[164,197],"methods":[167,190],"conclude":[169],"guaranteed":[174],"samples":[178],"corpus.":[183],"study":[185],"could":[191],"be":[192],"independent":[194],"interest.":[195],"Experiments":[196],"2.4":[201],"million":[202],"substantiate":[204],"analytical":[206],"findings":[207],"show":[209],"do":[213],"not":[214],"have":[215],"significant":[216],"towards":[218],"collect":[226],"comparative":[227],"statistics":[228],"about":[229],"corpora":[231],"Google,":[234],"MSN":[235],"Search,":[236],"Yahoo!":[238]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":16},{"year":2012,"cited_by_count":9}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}