{"id":"https://openalex.org/W2157204331","doi":"https://doi.org/10.1145/1242572.1242634","title":"Random web crawls","display_name":"Random web crawls","publication_year":2007,"publication_date":"2007-05-08","ids":{"openalex":"https://openalex.org/W2157204331","doi":"https://doi.org/10.1145/1242572.1242634","mag":"2157204331"},"language":"en","primary_location":{"id":"doi:10.1145/1242572.1242634","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1242572.1242634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th international conference on World Wide Web","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/A5060837195","display_name":"Toufik Bennouas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210161401","display_name":"Criteo (France)","ror":"https://ror.org/04vyg0r47","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210161401"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Toufik Bennouas","raw_affiliation_strings":["Criteo R & D, Paris, France"],"affiliations":[{"raw_affiliation_string":"Criteo R & D, Paris, France","institution_ids":["https://openalex.org/I4210161401"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001977542","display_name":"Fabien de Montgolfier","orcid":"https://orcid.org/0000-0002-3237-4256"},"institutions":[{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I4210094115","display_name":"Laboratoire d'Informatique Algorithmique: Fondements et Applications","ror":"https://ror.org/00pbqgm18","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I204730241","https://openalex.org/I4210094115","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fabien de Montgolfier","raw_affiliation_strings":["LIAFA - Universite Paris 7, Paris, France"],"affiliations":[{"raw_affiliation_string":"LIAFA - Universite Paris 7, Paris, France","institution_ids":["https://openalex.org/I4210094115","https://openalex.org/I204730241"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5060837195"],"corresponding_institution_ids":["https://openalex.org/I4210161401"],"apc_list":null,"apc_paid":null,"fwci":3.956,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.94362127,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"451","last_page":"460"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9739999771118164,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9569000005722046,"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":0.7930728197097778},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.6607046723365784},{"id":"https://openalex.org/keywords/hyperlink","display_name":"Hyperlink","score":0.5953640937805176},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5404850244522095},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5230085253715515},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.511214017868042},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.41851192712783813}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7930728197097778},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.6607046723365784},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.5953640937805176},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5404850244522095},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5230085253715515},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.511214017868042},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.41851192712783813},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1242572.1242634","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1242572.1242634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th international conference on World Wide Web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W64908208","https://openalex.org/W336063547","https://openalex.org/W1506285740","https://openalex.org/W1561637629","https://openalex.org/W1854214752","https://openalex.org/W2007687650","https://openalex.org/W2008620264","https://openalex.org/W2030035054","https://openalex.org/W2056380633","https://openalex.org/W2082137560","https://openalex.org/W2097147952","https://openalex.org/W2106178197","https://openalex.org/W2112090702","https://openalex.org/W2115579680","https://openalex.org/W2120407371","https://openalex.org/W2134122907","https://openalex.org/W2138621811","https://openalex.org/W2150596521","https://openalex.org/W2151626491","https://openalex.org/W2169263924","https://openalex.org/W2170582301","https://openalex.org/W2175110005","https://openalex.org/W2242296106","https://openalex.org/W2769133055","https://openalex.org/W4255068527","https://openalex.org/W4285719527","https://openalex.org/W6639055396","https://openalex.org/W6680132782"],"related_works":["https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2026132847","https://openalex.org/W4385695127","https://openalex.org/W2137810919","https://openalex.org/W2964752624","https://openalex.org/W4255854114","https://openalex.org/W2026661369"],"abstract_inverted_index":{"This":[0,20],"paper":[1,21],"proposes":[2],"a":[3,12,28,32,48,52,66,75],"random":[4,104],"Web":[5,9,29,49,96,105,127],"crawl":[6,10,30,50],"model.":[7],"A":[8],"is":[11,31,100],"(biased":[13],"and":[14,39,79],"partial)":[15],"image":[16],"of":[17,92,95,121,126],"the":[18,24,37,43,81,84,110,117,122],"Web.":[19],"deals":[22],"with":[23],"hyperlink":[25],"structure,":[26],"i.e.":[27,77],"graph,":[33],"whose":[34,40],"vertices":[35],"are":[36,42],"pages":[38],"edges":[41],"hypertextual":[44],"links.":[45],"Of":[46],"course":[47],"has":[51],"very":[53],"special":[54],"structure;":[55],"we":[56],"recall":[57],"some":[58],"known":[59,93],"results":[60],"about":[61],"it.":[62],"We":[63],"then":[64],"propose":[65],"model":[67,72,99],"generating":[68],"similar":[69],"structures.":[70],"Our":[71,98],"simply":[73],"simulates":[74],"crawling,":[76],"builds":[78],"crawls":[80],"graph":[82,106,128],"at":[83],"same":[85],"time.":[86],"The":[87],"graphs":[88],"generated":[89],"have":[90],"lot":[91],"properties":[94],"crawls.":[97],"simpler":[101],"than":[102],"most":[103],"models,":[107],"but":[108],"captures":[109],"sames":[111],"properties.":[112],"Notice":[113],"that":[114],"it":[115],"models":[116],"crawling":[118],"process":[119,125],"instead":[120],"page":[123],"writing":[124],"models.":[129]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}