{"id":"https://openalex.org/W3012679427","doi":"https://doi.org/10.1145/3366423.3380113","title":"Apophanies or Epiphanies? How Crawlers Impact Our Understanding of the Web","display_name":"Apophanies or Epiphanies? How Crawlers Impact Our Understanding of the Web","publication_year":2020,"publication_date":"2020-04-20","ids":{"openalex":"https://openalex.org/W3012679427","doi":"https://doi.org/10.1145/3366423.3380113","mag":"3012679427"},"language":"en","primary_location":{"id":"doi:10.1145/3366423.3380113","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366423.3380113","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3366423.3380113","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069036689","display_name":"Syed Suleman Ahmad","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Syed Suleman Ahmad","raw_affiliation_strings":["University of Wisconsin-Madison"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045896307","display_name":"Muhammad Daniyal Dar","orcid":null},"institutions":[{"id":"https://openalex.org/I126307644","display_name":"University of Iowa","ror":"https://ror.org/036jqmy94","country_code":"US","type":"education","lineage":["https://openalex.org/I126307644"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muhammad Daniyal Dar","raw_affiliation_strings":["University of Iowa"],"affiliations":[{"raw_affiliation_string":"University of Iowa","institution_ids":["https://openalex.org/I126307644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051828613","display_name":"Muhammad Fareed Zaffar","orcid":"https://orcid.org/0000-0002-1270-5513"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Muhammad Fareed Zaffar","raw_affiliation_strings":["LUMS"],"affiliations":[{"raw_affiliation_string":"LUMS","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016569835","display_name":"Narseo Vallina-Rodr\u00edguez","orcid":"https://orcid.org/0000-0002-5420-6835"},"institutions":[{"id":"https://openalex.org/I2802499160","display_name":"IMDEA Networks","ror":"https://ror.org/04mm9fg30","country_code":"ES","type":"facility","lineage":["https://openalex.org/I105140100","https://openalex.org/I2802499160"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Narseo Vallina-Rodriguez","raw_affiliation_strings":["IMDEA Networks/ICSI"],"affiliations":[{"raw_affiliation_string":"IMDEA Networks/ICSI","institution_ids":["https://openalex.org/I2802499160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046944830","display_name":"Rishab Nithyanand","orcid":"https://orcid.org/0000-0002-1280-1353"},"institutions":[{"id":"https://openalex.org/I126307644","display_name":"University of Iowa","ror":"https://ror.org/036jqmy94","country_code":"US","type":"education","lineage":["https://openalex.org/I126307644"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rishab Nithyanand","raw_affiliation_strings":["University of Iowa"],"affiliations":[{"raw_affiliation_string":"University of Iowa","institution_ids":["https://openalex.org/I126307644"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5069036689"],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":1.7835,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.87880401,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"271","last_page":"280"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9998000264167786,"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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9998000264167786,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9993000030517578,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/web-crawler","display_name":"Web crawler","score":0.895759105682373},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.8014780282974243},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7266618609428406},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.644530177116394},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.6300449371337891},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5099743604660034},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4895499646663666},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4159030318260193},{"id":"https://openalex.org/keywords/web-server","display_name":"Web server","score":0.1506938934326172}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.895759105682373},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8014780282974243},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7266618609428406},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.644530177116394},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.6300449371337891},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5099743604660034},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4895499646663666},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4159030318260193},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.1506938934326172},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3366423.3380113","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366423.3380113","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"}],"best_oa_location":{"id":"doi:10.1145/3366423.3380113","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366423.3380113","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/17","score":0.5199999809265137,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1916902331","https://openalex.org/W1965773314","https://openalex.org/W2012210084","https://openalex.org/W2015452169","https://openalex.org/W2016697314","https://openalex.org/W2046015955","https://openalex.org/W2072841881","https://openalex.org/W2108217512","https://openalex.org/W2117861756","https://openalex.org/W2121973001","https://openalex.org/W2123354009","https://openalex.org/W2135088779","https://openalex.org/W2141554582","https://openalex.org/W2149280729","https://openalex.org/W2159569559","https://openalex.org/W2274614582","https://openalex.org/W2283438976","https://openalex.org/W2344771039","https://openalex.org/W2415163239","https://openalex.org/W2489352404","https://openalex.org/W2535603283","https://openalex.org/W2554791272","https://openalex.org/W2561535538","https://openalex.org/W2743928556","https://openalex.org/W2751902902","https://openalex.org/W2769136280","https://openalex.org/W2782867239","https://openalex.org/W2793294490","https://openalex.org/W2801956435","https://openalex.org/W2806944993","https://openalex.org/W2821720247","https://openalex.org/W2891928976","https://openalex.org/W2902341081","https://openalex.org/W2918547900","https://openalex.org/W2947585023","https://openalex.org/W2956834532","https://openalex.org/W2994129655","https://openalex.org/W3015863761","https://openalex.org/W4300175397"],"related_works":["https://openalex.org/W2375180657","https://openalex.org/W4385695127","https://openalex.org/W4248730791","https://openalex.org/W2026132847","https://openalex.org/W1506122440","https://openalex.org/W2137810919","https://openalex.org/W2358310581","https://openalex.org/W2352686120","https://openalex.org/W2019080882","https://openalex.org/W2372594123"],"abstract_inverted_index":{"Data":[0],"generated":[1,53],"by":[2,71],"web":[3],"crawlers":[4,21,26,73,179],"has":[5,46],"formed":[6],"the":[7,16,42,51,68,75,89,104,115,153,176,182,191],"basis":[8],"for":[9,121,158],"much":[10],"of":[11,15,44,67,84,97,117,134,137,155,161,184,190],"our":[12,143,188],"current":[13],"understanding":[14,189],"Internet.":[17],"However,":[18],"not":[19],"all":[20,98,138],"are":[22],"created":[23],"equal":[24],"and":[25,39,54,74,107,113,125,169,180],"generally":[27],"find":[28],"themselves":[29],"trading":[30],"off":[31],"between":[32,178],"computational":[33],"overhead,":[34],"developer":[35],"effort,":[36],"data":[37,52,162],"accuracy,":[38],"completeness.":[40],"Therefore,":[41],"choice":[43,183],"crawler":[45,185],"a":[47,64,95,131,135,167,170],"critical":[48],"impact":[49,76,187],"on":[50,81],"knowledge":[55],"inferred":[56],"from":[57],"it.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62,93,129,165],"conduct":[63,94,130],"systematic":[65],"study":[66],"trade-offs":[69],"presented":[70],"different":[72,122],"that":[77],"these":[78],"can":[79,186],"have":[80],"various":[82],"types":[83,160],"measurement":[85,109,171],"studies.":[86],"We":[87],"make":[88],"following":[90],"contributions:":[91],"First,":[92],"survey":[96],"research":[99],"published":[100],"since":[101],"2015":[102],"in":[103,142],"premier":[105],"security":[106],"Internet":[108],"venues":[110],"to":[111,149,173],"identify":[112],"verify":[114],"repeatability":[116],"crawling":[118,139],"methodologies":[119],"deployed":[120],"problem":[123],"domains":[124],"publication":[126],"venues.":[127],"Next,":[128],"qualitative":[132],"evaluation":[133,146],"subset":[136],"tools":[140],"identified":[141],"survey.":[144],"This":[145],"allows":[147],"us":[148],"draw":[150],"conclusions":[151],"about":[152],"suitability":[154],"each":[156],"tool":[157],"specific":[159],"gathering.":[163],"Finally,":[164],"present":[166],"methodology":[168],"framework":[172],"empirically":[174],"highlight":[175],"differences":[177],"how":[181],"web.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}
