{"id":"https://openalex.org/W3004148183","doi":"https://doi.org/10.1145/3366423.3380104","title":"The Representativeness of Automated Web Crawls as a Surrogate for Human Browsing","display_name":"The Representativeness of Automated Web Crawls as a Surrogate for Human Browsing","publication_year":2020,"publication_date":"2020-04-20","ids":{"openalex":"https://openalex.org/W3004148183","doi":"https://doi.org/10.1145/3366423.3380104","mag":"3004148183"},"language":"en","primary_location":{"id":"doi:10.1145/3366423.3380104","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366423.3380104","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Web Conference 2020","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3366423.3380104","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067544139","display_name":"David Zeber","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"David Zeber","raw_affiliation_strings":["Mozilla","Mozilla (Canada)"],"affiliations":[{"raw_affiliation_string":"Mozilla","institution_ids":[]},{"raw_affiliation_string":"Mozilla (Canada)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008351642","display_name":"Sarah Bird","orcid":"https://orcid.org/0000-0002-5469-5149"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sarah Bird","raw_affiliation_strings":["Mozilla","Mozilla (Canada)"],"affiliations":[{"raw_affiliation_string":"Mozilla","institution_ids":[]},{"raw_affiliation_string":"Mozilla (Canada)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018108633","display_name":"C.J.S. Oliveira","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Camila Oliveira","raw_affiliation_strings":["Mozilla","Mozilla (Canada)"],"affiliations":[{"raw_affiliation_string":"Mozilla","institution_ids":[]},{"raw_affiliation_string":"Mozilla (Canada)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030605099","display_name":"Walter Rudametkin","orcid":"https://orcid.org/0000-0003-2903-7600"},"institutions":[{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]},{"id":"https://openalex.org/I4210126879","display_name":"Laboratoires Spiral (France)","ror":"https://ror.org/02c7hqm03","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210126879"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Walter Rudametkin","raw_affiliation_strings":["Univ. Lille / Inria","SPIRALS - Self-adaptation for distributed services and large software systems (France)"],"affiliations":[{"raw_affiliation_string":"Univ. Lille / Inria","institution_ids":["https://openalex.org/I2279609970"]},{"raw_affiliation_string":"SPIRALS - Self-adaptation for distributed services and large software systems (France)","institution_ids":["https://openalex.org/I4210126879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041180801","display_name":"Ilana Segall","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ilana Segall","raw_affiliation_strings":["Mozilla","Mozilla (Canada)"],"affiliations":[{"raw_affiliation_string":"Mozilla","institution_ids":[]},{"raw_affiliation_string":"Mozilla (Canada)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035142879","display_name":"Fredrik Wolls\u00e9n","orcid":"https://orcid.org/0009-0003-3095-0939"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fredrik Wolls\u00e9n","raw_affiliation_strings":["Mozilla","Mozilla (Canada)"],"affiliations":[{"raw_affiliation_string":"Mozilla","institution_ids":[]},{"raw_affiliation_string":"Mozilla (Canada)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022730811","display_name":"Martin Lopatka","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin Lopatka","raw_affiliation_strings":["Mozilla","Mozilla (Canada)"],"affiliations":[{"raw_affiliation_string":"Mozilla","institution_ids":[]},{"raw_affiliation_string":"Mozilla (Canada)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5067544139"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.1202,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.96498803,"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":"167","last_page":"178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9987999796867371,"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":0.9987999796867371,"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/T12720","display_name":"Multimedia Communication and Technology","score":0.9889000058174133,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9672999978065491,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/representativeness-heuristic","display_name":"Representativeness heuristic","score":0.8928459882736206},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7245913743972778},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.47253158688545227},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4330011010169983},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05831706523895264},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.050347864627838135}],"concepts":[{"id":"https://openalex.org/C37381756","wikidata":"https://www.wikidata.org/wiki/Q20203288","display_name":"Representativeness heuristic","level":2,"score":0.8928459882736206},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7245913743972778},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.47253158688545227},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4330011010169983},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05831706523895264},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.050347864627838135}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3366423.3380104","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366423.3380104","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Web Conference 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-02456195v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-02456195","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"The Web Conference, Apr 2020, Taipei, Taiwan. ⟨10.1145/3366423.3380104⟩","raw_type":"Conference papers"},{"id":"pmh:oai:lilloa.univ-lille.fr:20.500.12210/21919","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.12210/21919","pdf_url":null,"source":{"id":"https://openalex.org/S4306402203","display_name":"LillOA (Universit\u00e9 de Lille (University Of Lille))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210123514","host_organization_name":"Centre d'Etudes en Civilisations, Langues et Litt\u00e9ratures Etrang\u00e8res","host_organization_lineage":["https://openalex.org/I4210123514"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3366423.3380104","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366423.3380104","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Web Conference 2020","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6399999856948853,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G8318455765","display_name":null,"funder_award_id":"ANR-19","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1475732121","https://openalex.org/W1530813112","https://openalex.org/W1966175380","https://openalex.org/W1972524097","https://openalex.org/W2110073539","https://openalex.org/W2113184419","https://openalex.org/W2113235062","https://openalex.org/W2115022330","https://openalex.org/W2175110005","https://openalex.org/W2201484187","https://openalex.org/W2297075900","https://openalex.org/W2341516340","https://openalex.org/W2482685351","https://openalex.org/W2505140917","https://openalex.org/W2508271471","https://openalex.org/W2535603283","https://openalex.org/W2575436837","https://openalex.org/W2733005124","https://openalex.org/W2743928556","https://openalex.org/W2751069419","https://openalex.org/W2889000693","https://openalex.org/W2891928976","https://openalex.org/W2924075319","https://openalex.org/W2946113142","https://openalex.org/W2950337464","https://openalex.org/W2957547225","https://openalex.org/W2986967943","https://openalex.org/W2997134027","https://openalex.org/W4295023194","https://openalex.org/W4299930775","https://openalex.org/W4391156274"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3159631231","https://openalex.org/W4306248409","https://openalex.org/W4211213551","https://openalex.org/W2332151799","https://openalex.org/W2062728131","https://openalex.org/W1824075546","https://openalex.org/W2103926897"],"abstract_inverted_index":{"Large-scale":[0],"Web":[1,28,93,121,196],"crawls":[2,38,64,97,122,135,172],"have":[3,72],"emerged":[4],"as":[5,37,55,65],"the":[6,9,15,59,82,88,92,116,151,169,194,203,235],"state":[7],"of":[8,14,84,91,108,120,125,146,153,177,189,193,205,224],"art":[10],"for":[11,24,68,215],"studying":[12],"characteristics":[13],"Web.":[16],"In":[17,111],"particular,":[18],"they":[19],"are":[20],"a":[21,66,165,174],"core":[22],"tool":[23],"online":[25],"tracking":[26,127],"research.":[27],"crawling":[29,207],"is":[30],"an":[31,186],"attractive":[32],"approach":[33],"to":[34,80,167,220],"data":[35,53,71],"collection,":[36],"can":[39],"be":[40],"run":[41],"at":[42],"relatively":[43],"low":[44],"infrastructure":[45,208],"cost":[46],"and":[47,87,118,128,136,160,180,209],"don\u2019t":[48],"require":[49],"handling":[50],"sensitive":[51],"user":[52,85],"such":[54],"browsing":[56,70,182],"histories.":[57],"However,":[58],"biases":[60],"introduced":[61],"by":[62,95],"using":[63],"proxy":[67],"human":[69,139,212,228],"not":[73,99],"been":[74],"well":[75],"studied.":[76],"Crawls":[77],"may":[78],"fail":[79],"capture":[81],"diversity":[83],"environments,":[86],"snapshot":[89],"view":[90],"presented":[94],"one-time":[96],"does":[98],"reflect":[100],"its":[101],"constantly":[102],"evolving":[103],"nature,":[104],"which":[105],"hinders":[106],"reproducibility":[107],"crawl-based":[109],"studies.":[110],"this":[112],"paper,":[113],"we":[114],"quantify":[115,143],"repeatability":[117],"representativeness":[119],"in":[123],"terms":[124],"common":[126],"fingerprinting":[129],"metrics,":[130],"considering":[131],"both":[132],"variation":[133,145],"across":[134],"divergence":[137],"from":[138,185,234],"browser":[140,229],"usage.":[141],"We":[142],"baseline":[144],"simultaneous":[147],"crawls,":[148],"then":[149],"isolate":[150],"effects":[152],"time,":[154],"cloud":[155],"IP":[156],"address":[157],"vs.":[158],"residential,":[159],"operating":[161],"system.":[162],"This":[163],"provides":[164],"foundation":[166],"assess":[168],"agreement":[170],"between":[171,202],"visiting":[173],"standard":[175],"list":[176],"high-traffic":[178],"websites":[179],"actual":[181],"behaviour":[183],"measured":[184],"opt-in":[187],"sample":[188],"over":[190],"50,000":[191],"users":[192,230],"Firefox":[195],"browser.":[197],"Our":[198],"analysis":[199],"reveals":[200],"differences":[201],"treatment":[204],"stateless":[206],"generally":[210],"stateful":[211],"browsing,":[213],"showing,":[214],"example,":[216],"that":[217],"crawlers":[218],"tend":[219],"experience":[221],"higher":[222],"rates":[223],"third-party":[225],"activity":[226],"than":[227],"on":[231],"loading":[232],"pages":[233],"same":[236],"domains.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}